-
Notifications
You must be signed in to change notification settings - Fork 0
/
diploma1.bib
2013 lines (1920 loc) · 105 KB
/
diploma1.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
@inproceedings{bu2010music,
author = {Bu, Jiajun and Tan, Shulong and Chen, Chun and Wang, Can and Wu, Hao and Zhang, Lijun and He, Xiaofei},
booktitle = {Proceedings of the international conference on Multimedia},
organization = {ACM},
pages = {391--400},
title = {{Music recommendation by unified hypergraph: combining social media information and music content}},
year = {2010}
}
@book{lawrence2008fundamentals,
author = {Lawrence, Rabiner},
publisher = {Pearson Education India},
title = {{Fundamentals of speech Recognition}},
year = {2008}
}
@inproceedings{julier1997consistent,
author = {Julier, Simon J and Uhlmann, Jeffrey K},
booktitle = {AeroSense'97},
organization = {International Society for Optics and Photonics},
pages = {110--121},
title = {{Consistent debiased method for converting between polar and Cartesian coordinate systems}},
year = {1997}
}
@inproceedings{susstrunk1999standard,
author = {S\"{u}sstrunk, Sabine and Buckley, Robert and Swen, Steve},
booktitle = {Color and Imaging Conference},
number = {1},
organization = {Society for Imaging Science and Technology},
pages = {127--134},
title = {{Standard RGB color spaces}},
volume = {1999},
year = {1999}
}
@inproceedings{Sural2002,
author = {Sural, S. and Pramanik, S.},
booktitle = {Proceedings. International Conference on Image Processing},
doi = {10.1109/ICIP.2002.1040019},
isbn = {0-7803-7622-6},
issn = {1522-4880},
keywords = {Content based retrieval,Feature extraction,HSV color space,Histograms,Image analysis,Image color analysis,Image retrieval,Image segmentation,Pixel,RGB color space,Smoothing methods,Visual perception,content based image retrieval,content-based retrieval,feature extraction,histogram generation,hue value,image colour analysis,image pixel,image retrieval,image segmentation,intensity value,object identification,pixel features extraction,saturation value,smoothing methods,statistical analysis,uniform color transition,visual databases,visual perception,window-based smoothing},
language = {English},
pages = {II--589--II--592},
publisher = {IEEE},
title = {{Segmentation and histogram generation using the HSV color space for image retrieval}},
url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=1040019},
volume = {2},
year = {2002}
}
@inproceedings{chen2001music,
author = {Chen, Hung-Chen and Chen, Arbee L P},
booktitle = {Proceedings of the tenth international conference on Information and knowledge management},
organization = {ACM},
pages = {231--238},
title = {{A music recommendation system based on music data grouping and user interests}},
year = {2001}
}
@incollection{JaeSikLee2006,
address = {Berlin, Heidelberg},
author = {{Jae Sik Lee}, Jin Chun Lee},
booktitle = {Smart Sensing and Context},
doi = {10.1007/11907503},
editor = {Havinga, Paul and Lijding, Maria and Meratnia, Nirvana and Wegdam, Maarten},
isbn = {978-3-540-47842-3},
pages = {190--203},
publisher = {Springer Berlin Heidelberg},
series = {Lecture Notes in Computer Science},
title = {{Music for My Mood: A Music Recommendation System Based on Context Reasoning}},
url = {http://www.springerlink.com/index/10.1007/11907503},
volume = {4272},
year = {2006}
}
@article{Li2007,
author = {Li, Yipeng and Wang, DeLiang},
doi = {10.1109/TASL.2006.889789},
issn = {1558-7916},
journal = {IEEE Transactions on Audio, Speech and Language Processing},
keywords = {Auditory system,Automatic speech recognition,Cognitive science,Computer science,Humans,Instruments,Laboratories,Music information retrieval,Predominant pitch detection,Speech recognition,Time frequency analysis,audio recording,lyrics recognition,monaural recordings,music,music accompaniment,music information retrieval,predominant pitch detection,singer identification,singing voice detection,singing voice separation,sound separation,speech processing,speech recognition,time-frequency segments,track seperation},
language = {English},
mendeley-tags = {track seperation},
month = may,
number = {4},
pages = {1475--1487},
publisher = {IEEE},
title = {{Separation of Singing Voice From Music Accompaniment for Monaural Recordings}},
url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=4156205},
volume = {15},
year = {2007}
}
@article{Gillet2008,
author = {Gillet, O. and Richard, G.},
doi = {10.1109/TASL.2007.914120},
issn = {1558-7916},
journal = {IEEE Transactions on Audio, Speech, and Language Processing},
keywords = {Drum signals,Wiener filtering,Wiener filtering-based separation method,Wiener filters,audio signal processing,drum signals separation,drum signals transcription,drum track extraction,feature selection,filtering theory,fusion strategies,harmonic-noise decomposition,harmonic/noise decomposition,music,music transcription,musical instruments,polyphonic music,source separation,support vector machine (SVM),time-frequency analysis,time-frequency masking,track seperation},
language = {English},
mendeley-tags = {track seperation},
month = mar,
number = {3},
pages = {529--540},
publisher = {IEEE},
title = {{Transcription and Separation of Drum Signals From Polyphonic Music}},
url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=4443887},
volume = {16},
year = {2008}
}
@inproceedings{bogdanov2013essentia,
author = {Bogdanov, Dmitry and Wack, Nicolas and G\'{o}mez, Emilia and Gulati, Sankalp and Herrera, Perfecto and Mayor, Oscar and Roma, Gerard and Salamon, Justin and Zapata, Jos\'{e} R and Serra, Xavier},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
organization = {Citeseer},
pages = {493--498},
title = {{Essentia: An Audio Analysis Library for Music Information Retrieval.}},
year = {2013}
}
@inproceedings{saari2013role,
author = {Saari, Pasi and Eerola, Tuomas and Fazekas, Gy\"{o}rgy and Barthet, Mathieu and Lartillot, Olivier and Sandler, Mark B},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
pages = {201--206},
title = {{The Role of Audio and Tags in Music Mood Prediction: A Study Using Semantic Layer Projection.}},
year = {2013}
}
@inproceedings{watson2012modeling,
author = {Watson, Diane and Mandryk, Regan L},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
pages = {31--36},
title = {{Modeling Musical Mood From Audio Features and Listening Context on an In-Situ Data Set.}},
year = {2012}
}
@inproceedings{chu2010lamp,
author = {Chu, Wei-rong and Tsai, RT-H and Wu, Ying-Sian and Wu, Hui-Hsin and Chen, Hung-Yi and Hsu, JY-J},
booktitle = {Technologies and Applications of Artificial Intelligence (TAAI), 2010 International Conference on},
organization = {IEEE},
pages = {53--59},
title = {{LAMP, a lyrics and audio mandopop dataset for music mood estimation: Dataset compilation, system construction, and testing}},
year = {2010}
}
@phdthesis{pesek2012prepoznavanje,
author = {Pesek, Matev\v{z}},
school = {M. Pesek},
title = {{Prepoznavanje akordov s hierarhi\{\v{c}\}nim kompozicionalnim modelom: diplomsko delo}},
year = {2012}
}
@article{la2001harmonic,
author = {{La Rue}, Jan},
journal = {The Journal of Musicology},
number = {2},
pages = {221--248},
publisher = {JSTOR},
title = {{Harmonic Rhythm in the Beethoven symphonies}},
volume = {18},
year = {2001}
}
@article{terhardt1974pitch,
author = {Terhardt, Ernst},
journal = {The Journal of the Acoustical Society of America},
number = {5},
pages = {1061--1069},
publisher = {Acoustical Society of America},
title = {{Pitch, consonance, and harmony}},
volume = {55},
year = {1974}
}
@inproceedings{zhu2005music,
author = {Zhu, Yongwei and Kankanhalli, Mohan S and Gao, Sheng},
booktitle = {Multimedia Modelling Conference, 2005. MMM 2005. Proceedings of the 11th International},
organization = {IEEE},
pages = {30--37},
title = {{Music key detection for musical audio}},
year = {2005}
}
@inproceedings{gouyon2000classifying,
author = {Gouyon, F and Delerue, O and Pachet, F},
booktitle = {Proceedings of the COST G-6 Conference on Digital Audio Effects},
title = {{Classifying percussive sounds: a matter of zero-crossing rate?}},
year = {2000}
}
@inproceedings{brossier2004real,
author = {Brossier, Paul and Bello, Juan Pablo and Plumbley, Mark D},
booktitle = {Proceedings of the ICMC},
title = {{Real-time temporal segmentation of note objects in music signals}},
year = {2004}
}
@inproceedings{gouyon2001exploration,
author = {Gouyon, Fabien and Herrera, Perfecto},
booktitle = {Proceedings of MOSART: Workshop on Current Directions in Computer Music},
title = {{Exploration of techniques for automatic labeling of audio drum tracks instruments}},
year = {2001}
}
@article{gunderson2007musical,
author = {Gunderson, Steinar Heimdal},
publisher = {Institutt for elektronikk og telekommunikasjon},
title = {{Musical descriptors: An assessment of psychoacoustical models in the presence of lossy compression}},
year = {2007}
}
@phdthesis{bogdanov2013form,
address = {Barcelona, Spain},
author = {Bogdanov, D},
keywords = { music information retrieval, music recommendation, music similarity, personalization, preference elicitation, recommender systems, user modeling, visualization,music discovery},
pages = {227},
school = {Universitat Pompeu Fabra},
title = {{From music similarity to music recommendation: Computational approaches based on audio features and metadata}},
year = {2013}
}
@book{lenko2009pomen,
author = {Lenko, Mira and Kogov\v{s}ek, Tina and Stankovi\'{c}, Peter},
publisher = {M. Lenko},
title = {{Pomen glasbe v o\v{c}eh mladih: diplomsko delo}},
year = {2009}
}
@incollection{Krause2012,
address = {London},
author = {Krause, Bernie},
booktitle = {The Great Animal Orchestra: Finding the Origins of Music in the World's Wild Places},
chapter = {Echonest o},
pages = {5--10},
publisher = {Hachette Digital, Inc.},
title = {{Echonest of the past}},
year = {2012}
}
@incollection{Wallin2001,
author = {Wallin, Nils Lenart and {Merker Bjorn} and Brown, Steven},
booktitle = {The origins of music},
publisher = {MIT Press},
title = {{The origins of music}},
year = {2001}
}
@inproceedings{Pesek2013c,
author = {Pesek, Matev\v{z} and Guna, Jo\v{z}e and Leonardis, Ale\v{s} and Marolt, Matija},
booktitle = {Proceedings of the 4th International Conference World Usability Day Slovenia 2013},
pages = {56--59},
title = {{Visualization of a deep architecture using the compositional hierarchical model}},
year = {2013}
}
@inproceedings{Woolhouse2006,
address = {Bologna},
author = {Woolhouse, Matthew and Cross, Ian and Horton, Timothy},
booktitle = {Proceedings of International Conference on Music Perception and Cognition},
title = {{The perception of non-adjecent harmonic relations}},
year = {2006}
}
@inproceedings{Hinton1983,
author = {Hinton, Geoffrey E and Sejnowski, Terrence J},
booktitle = {Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR)},
pages = {448--453},
title = {{Optimal Perceptual Inference}},
year = {1983}
}
@book{Lerdahl1983,
author = {Lerdahl, Fred and Jackendoff, Ray},
publisher = {Cambridge: MIT Press},
title = {{A generative theory of tonal music}},
year = {1983}
}
@inproceedings{ShigekiSagayama2004,
address = {Jeju, Korea},
author = {Sagayama, Shigeki and Takahashi, Keigo},
booktitle = {ISCA Tutorial and Research Workshop on Statistical and Perceptual Audio Processing},
title = {{Specmurt anasylis: A piano-roll-visualization of polyphonic music signal by deconvolution of log-frequency spectrum}},
year = {2004}
}
@article{schuller2010mister,
author = {Schuller, Bj\"{o}rn and Hage, Clemens and Schuller, Dagmar and Rigoll, Gerhard},
journal = {Journal of New Music Research},
number = {1},
pages = {13--34},
publisher = {Taylor \& Francis},
title = {{‘Mister DJ, Cheer Me Up!’: Musical and textual features for automatic mood classification}},
volume = {39},
year = {2010}
}
@inproceedings{Kashino1995,
address = {Quebec},
author = {Kashino, Kunio and Nakadai, Kazuhiro and Kinoshita, Tomoyoshi and Tanaka, Hidehiko},
booktitle = {International Joint Conference on Artificial Intelligence},
pages = {158--164},
title = {{Organization of Hierarchical Perceptual Sounds: Music Scene Analysis with Autonomous Processing Modules and a Quantitative Information Integration Mechanism}},
url = {http://citeseer.uark.edu:8380/citeseerx/showciting;jsessionid=D58CCAED426097BA141A1A6547B06F36?cid=3408864},
year = {1995}
}
@inproceedings{Pikrakis2013,
author = {Pikrakis, Aggelos},
booktitle = {6th International Workshop on Machine Learning and Music, held in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML/PKDD 2013},
pages = {1--4},
title = {{A Deep Learning Approach to Rhythm Modelling with Applications}},
year = {2013}
}
@book{Temperley2007,
author = {Temperley, David},
pages = {244},
publisher = {MIT Press},
title = {{Music and probability}},
year = {2007}
}
@article{Foote1999,
author = {Foote, Jonathan},
journal = {Multimedia Systems},
number = {1},
pages = {2--10},
title = {{An overview of audio information retrieval}},
url = {http://link.springer.com/article/10.1007/s005300050106?LI=true\#page-1},
volume = {7},
year = {1999}
}
@inproceedings{Mauch2008a,
address = {Sapporo},
author = {Mauch, Matthias and M\"{u}llensiefen, Daniel and Dixon, Simon and Wiggins, Geraint},
booktitle = {Proceedings of International Conference of Music Perception and Cognition},
title = {{Can Statistical Language Models be Used for the Analysis of Harmonic Progressions?}},
year = {2008}
}
@inproceedings{schmidt2009projection,
author = {Schmidt, Erik M and Kim, Youngmoo E},
booktitle = {10th International Society for Music Information Retrieval Conference. ISMIR},
title = {{Projection of acoustic features to continuous valence-arousal mood labels via regression}},
year = {2009}
}
@article{Hassenzahl2003,
author = {Hassenzahl, M and Burmester, M and Koller, F},
journal = {Mensch \& Computer},
title = {{AttrakDiff: A questionnaire to measure perceived hedonic and pragmatic quality}},
url = {http://scholar.google.si/scholar?hl=en\&q=attrakdiff\&btnG=\&as\_sdt=1,5\&as\_sdtp=\#1},
year = {2003}
}
@inproceedings{Pesek2013b,
address = {Ljubljana},
author = {Pesek, Matev\v{z} and Poredo\v{s}, Mojca and Guna, Jo\v{z}e and Stojmenova, Emilija and Marolt, Matija},
booktitle = {Proceedings of the 4th International Conference World Usability Day Slovenia 2013},
pages = {53--55},
title = {{Mood-dependent visual representation of audio recordings for music recommendation}},
year = {2013}
}
@article{Roebel2010,
author = {Roebel, Axel and Rodet, Xavier},
doi = {10.1109/TASL.2009.2030006},
issn = {1558-7916},
journal = {IEEE Transactions on Audio, Speech, and Language Processing},
number = {6},
pages = {1116--1126},
publisher = {IEEE},
title = {{Multiple Fundamental Frequency Estimation and Polyphony Inference of Polyphonic Music Signals}},
url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=5200519},
volume = {18},
year = {2010}
}
@article{Ellis2006,
author = {Ellis, Daniel P W and Poliner, Graham E},
doi = {10.1007/s10994-006-8373-9},
issn = {0885-6125},
journal = {Machine Learning},
number = {2-3},
pages = {439--456},
title = {{Classification-based melody transcription}},
url = {http://link.springer.com/10.1007/s10994-006-8373-9},
volume = {65},
year = {2006}
}
@inproceedings{Pesek2013,
author = {Pesek, Matev\v{z} and Marolt, Matija},
booktitle = {6th International Workshop on Machine Learning and Music, held in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML/PKDD 2013},
title = {{Chord estimation using compositional hierarchical model}},
year = {2013}
}
@inproceedings{Scholz2009,
abstract = {The modeling of music as a language is a core issue for a wide range of applications such as polyphonic music retrieval, automatic style identification, audio to symbolic music transcription and computer-assisted composition. In this paper, we focus on the modeling of chord sequences by probabilistic N-grams. Previous studies using these models have achieved limited success, due to overfitting and to the use of a single chord labeling scheme. We investigate these issues using model smoothing and selection techniques initially designed for spoken language modeling. This approach is evaluated over a set of songs by The Beatles, considering several chord labeling schemes. Initial results show that the accuracy of N-grams is increased but that additional improvements may still be achieved in the future using more advanced, possibly music-specific, smoothing techniques.},
author = {Scholz, Ricardo and Vincent, Emmanuel and Bimbot, Frederic},
booktitle = {Proceedings of International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
doi = {10.1109/ICASSP.2009.4959518},
isbn = {978-1-4244-2353-8},
issn = {1520-6149},
keywords = {Dictionaries,Hidden Markov models,History,Labeling,Music,Music information retrieval,N-grams,Natural languages,Robustness,Smoothing methods,Testing,Training data,audio-to-symbolic music transcription,automatic style identification,computer-assisted composition,information retrieval,model selection,model smoothing,model smoothing techniques,musical chord sequences,polyphonic music retrieval,probabilistic N-grams,probabilistic modeling,probability,single chord labeling scheme},
month = apr,
pages = {53--56},
publisher = {IEEE},
shorttitle = {Acoustics, Speech and Signal Processing, 2009. ICA},
title = {{Robust modeling of musical chord sequences using probabilistic N-grams}},
url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4959518},
year = {2009}
}
@article{Tolonen2000,
author = {Tolonen, Tero and Karjalainen, Matti},
journal = {IEEE Transactions on Speech and Audio Processing},
number = {6},
pages = {708--716},
title = {{A computationally Efficient Multipitch Analysis Model}},
volume = {8},
year = {2000}
}
@article{Bangor2009,
author = {Bangor, Aaron and Kortum, Philip and Miller, James},
journal = {Journal of Usability Studies},
number = {3},
title = {{Determining What Individual SUS Scores Mean: Adding an Adjective Rating Scale}},
volume = {4},
year = {2009}
}
@inproceedings{Farbook2010,
address = {Seattle},
author = {Farbood, Morwaread},
booktitle = {Proceedings of International Conference of Music Perception and Cognition},
title = {{Working memory and the perception of hierarchical tonal structures}},
year = {2010}
}
@inproceedings{Humphrey2012a,
address = {New York},
author = {Humphrey, Eric J and Cho, Taemin and Bello, Juan P},
booktitle = {Acoustics, Speech and Signal Processing (ICASSP)},
pages = {453--456},
title = {{Learning a Robust Tonnetz-Space Transform for Automatic Chord recognition}},
year = {2012}
}
@inproceedings{Klapuri,
author = {Klapuri, A P},
booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, 2005.},
doi = {10.1109/ASPAA.2005.1540227},
isbn = {0-7803-9154-3},
keywords = {Acoustic signal processing,Auditory system,Computational modeling,Computer peripherals,Frequency estimation,Humans,Multiple signal classification,Music,Signal analysis,Signal processing,acoustic signal detection,concurrent musical sounds,human auditory periphery,multiple-fundamental frequency estimation method,periodicity analysis mechanism,peripheral hearing model},
pages = {291--294},
publisher = {IEEE},
title = {{A perceptually motivated multiple-F0 estimation method}},
url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=1540227},
year = {2005}
}
@inproceedings{MattiRyynanen2006,
author = {Ryyn\"{a}nen, Matti and Klapuri, Anssi},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
pages = {222--227},
title = {{Transcription of the singing melody in polyphonic music}},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.79.7724},
year = {2006}
}
@article{Colibazzi2010,
abstract = {The circumplex model of affect construes all emotions as linear combinations of 2 independent neurophysiological dimensions, valence and arousal. We used functional magnetic resonance imaging to identify the neural networks subserving valence and arousal, and we assessed, in 10 participants, the associations of the BOLD (blood oxygen level-dependent) response, an indirect index of neural activity, with ratings of valence and arousal during the emotional experiences induced by the presentation of evocative sentences. Unpleasant emotional experience was associated with increased BOLD signal intensities in the supplementary motor, anterior midcingulate, right dorsolateral prefrontal, occipito-temporal, inferior parietal, and cerebellar cortices. Highly arousing emotions were associated with increased BOLD signal intensities in the left thalamus, globus pallidus, caudate, parahippocampal gyrus, amygdala, premotor cortex, and cerebellar vermis. Separate analyses using a finite impulse response model confirmed these results and revealed that pleasant emotions engaged an additional network that included the midbrain, ventral striatum, and caudate nucleus, all portions of a reward circuit. These findings suggest the existence of distinct networks subserving the valence and arousal dimensions of emotions, with midline and medial temporal lobe structures mediating arousal and dorsal cortical areas and mesolimbic pathways mediating valence.},
author = {Colibazzi, Tiziano and Posner, Jonathan and Wang, Zhishun and Gorman, Daniel and Gerber, Andrew and Yu, Shan and Zhu, Hongtu and Kangarlu, Alayar and Duan, Yunsuo and Russell, James A and Peterson, Bradley S},
doi = {10.1037/a0018484},
issn = {1931-1516},
journal = {Emotion (Washington, D.C.)},
keywords = {Adult,Amygdala,Amygdala: physiology,Arousal,Arousal: physiology,Brain,Brain: physiology,Caudate Nucleus,Caudate Nucleus: physiology,Cerebellar Cortex,Cerebellar Cortex: physiology,Emotions,Emotions: physiology,Female,Globus Pallidus,Globus Pallidus: physiology,Humans,Magnetic Resonance Imaging,Male,Parahippocampal Gyrus,Parahippocampal Gyrus: physiology,Thalamus,Thalamus: physiology,Young Adult},
number = {3},
pages = {377--389},
pmid = {20515226},
title = {{Neural systems subserving valence and arousal during the experience of induced emotions.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/20515226},
volume = {10},
year = {2010}
}
@inproceedings{Boulanger-Lewandowski2011,
author = {Boulanger-Lewandowski, N and Vincent, P and Bengio, Yoshua},
booktitle = {Snowbird Learning workshop},
title = {{Energy-based Recurrent Neural Network for Multiple Fundamental Frequency Estimation}},
year = {2011}
}
@article{McDermott2008,
author = {McDermott, Josh H and Oxenham, Andrew J},
journal = {Current opinion in Neurobiology},
number = {18},
pages = {452--463},
title = {{Music perception, pitch and the auditory system}},
year = {2008}
}
@article{SJ2009,
author = {Morrison, Stephen J and Demorest, Stephen M},
journal = {Progress in brain research},
number = {178},
pages = {67--77},
title = {{Cultural constraints on music perception and cognition}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/19874962},
year = {2009}
}
@book{Rosenblatt1962,
author = {Rosenblatt, Frank},
pages = {616},
publisher = {Spartan Books},
title = {{Principles of neurodynamics: perceptrons and the theory of brain mechanisms}},
url = {http://books.google.ca/books/about/Principles\_of\_neurodynamics.html?id=7FhRAAAAMAAJ\&pgis=1},
year = {1962}
}
@inproceedings{schmidt2010prediction,
author = {Schmidt, Erik M and Kim, Youngmoo E},
booktitle = {ISMIR},
pages = {465--470},
title = {{Prediction of Time-varying Musical Mood Distributions from Audio.}},
year = {2010}
}
@article{Paraskevopoulos2010,
author = {Paraskevopoulos, Evangelos and Tsapkini, Kyrana and Peretz, Isabelle},
journal = {Journal of the International Neuropsychological Society},
number = {4},
pages = {1--10},
title = {{Cultural aspects of music perception: Validation of a Greek version of the Montreal Battery of Evaluation of Amusias}},
volume = {16},
year = {2010}
}
@inproceedings{Hamel2010,
author = {Hamel, Philippe and Eck, Douglas},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
pages = {339--344},
title = {{Learning Features from Music Audio with Deep Belief Networks}},
year = {2010}
}
@inproceedings{LardeurERHS09_ClassAudioProduction_ICASSP,
author = {Lardeur, M and Essid, S and Richard, G and Haller, M and Sikora, T},
booktitle = {Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on},
doi = {10.1109/ICASSP.2009.4959918},
issn = {1520-6149},
month = apr,
pages = {1653--1656},
title = {{Incorporating prior knowledge on the digital media creation process into audio classifiers}},
year = {2009}
}
@article{Braun1999,
author = {Braun, Martin},
journal = {Hearing Research},
pages = {71--82},
title = {{Audtiroy midbrain laminar structure appears adapted to f0 extraction: further evidence and implications of the double critical bandwidth}},
volume = {129},
year = {1999}
}
@article{Bengio2009,
author = {Bengio, Yoshua},
journal = {Foundations and Trends® in Machine Learning},
number = {1},
pages = {1--127},
publisher = {Foundations and Trends in Machine Learning},
title = {{Learning Deep Architectures for AI}},
volume = {2},
year = {2009}
}
@inproceedings{Noland2006,
address = {Victoria},
author = {Noland, Katy and Sandler, Mark},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
title = {{Key Estimation Using a Hidden Markov Model}},
year = {2006}
}
@inproceedings{Boulanger-Lewandowski2013,
author = {Boulanger-Lewandowski, Nicolas and Bengio, Yoshua and Vincent, Pascal},
booktitle = {2013 IEEE International Conference on Acoustics, Speech and Signal Processing},
doi = {10.1109/ICASSP.2013.6638244},
isbn = {978-1-4799-0356-6},
issn = {1520-6149},
keywords = {Accuracy,Hidden Markov models,Noise,Recurrent neural networks,Sequence transduction,Smoothing methods,Training,Vectors,acoustic transducers,audio signal processing,error statistics,global distribution mode,high dimensional output sequence,high dimensional sequence transduction,music,musically plausible transcription,polyphonic audio music,polyphonic transcription,probabilistic model,probability,realistic output distribution,recurrent neural nets,recurrent neural network,restricted Boltzmann machine,symbolic notation,test error rate},
pages = {3178--3182},
publisher = {IEEE},
title = {{High-dimensional sequence transduction}},
url = {http://ieeexplore.ieee.org/articleDetails.jsp?arnumber=6638244},
year = {2013}
}
@book{Gelfand2004,
author = {Gelfand, Stanley A},
pages = {312},
title = {{Hearing: An introduction to psychological and physiological acoustics}},
year = {2004}
}
@incollection{Fidler2009,
author = {Fidler, Sanja and Boben, Marko and Leonardis, Ale\v{s}},
booktitle = {Object Categorization: Computer and Human Vision Perspectives},
pages = {196--215},
publisher = {Cambridge University Press},
title = {{Learning Hierarchical Compositional Representations of Object Structure}},
year = {2009}
}
@article{Melara1989,
author = {Melara, Robert D},
journal = {Journal of Experimental Psychology: Human Perception and Performacne},
number = {1},
pages = {69--79},
title = {{Dimensional Interaction Between Color and Pitch}},
volume = {15},
year = {1989}
}
@article{Amitay2006,
author = {Amitay, Sygal and Irwin, Amy and Moore, David R},
journal = {Nature Neuroscience},
number = {11},
pages = {1446--1448},
title = {{Discrimination learning induced by training with identical stimuli}},
volume = {9},
year = {2006}
}
@article{Hart2006,
author = {Hart, S G},
doi = {10.1177/154193120605000909},
issn = {1071-1813},
journal = {Proceedings of the Human Factors and Ergonomics Society Annual Meeting},
number = {9},
pages = {904--908},
publisher = {SAGE Publications},
title = {{Nasa-Task Load Index (NASA-TLX); 20 Years Later}},
url = {http://pro.sagepub.com/content/50/9/904.abstract},
volume = {50},
year = {2006}
}
@inproceedings{Pesek2014b,
author = {Pesek, Matev\v{z} and Godec, Primo\v{z} and Poredo\v{s}, Mojca and Strle, Gregor and Guna, Jo\v{z}e and Stojmenova, Emilija and Poga\v{c}nik, Matev\v{z} and Marolt, Matija},
booktitle = {Management Information Systems in Multimedia Art, Education, Entertainment, and Culture (MIS-MEDIA), IEEE Internation Conference on Multimedia \& Expo (ICME)},
pages = {1--4},
title = {{Capturing the Mood: Evaluation of the MoodStripe and MoodGraph Interfaces}},
year = {2014}
}
@article{Yu2011,
abstract = {The purpose of this article is to introduce the readers to the emerging technologies enabled by deep learning and to review the research work conducted in this area that is of direct relevance to signal processing. We also point out, in our view, the future research directions that may attract interests of and require efforts from more signal processing researchers and practitioners in this emerging area for advancing signal and information processing technology and applications.},
author = {Yu, Dong and Deng, Li},
doi = {10.1109/MSP.2010.939038},
issn = {1053-5888},
journal = {IEEE Signal Processing Magazine},
number = {1},
pages = {145--154},
shorttitle = {Signal Processing Magazine, IEEE},
title = {{Deep Learning and Its Applications to Signal and Information Processing [Exploratory DSP}},
url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5670617},
volume = {28},
year = {2011}
}
@techreport{Gerhard,
address = {Regina},
author = {Gerhard, David},
institution = {University of Regina, Saskatchewan, Canada},
keywords = {Technical Report TR-CS},
mendeley-tags = {Technical Report TR-CS},
title = {{Pitch Extraction and Fundamental Frequency: History and Current Techniques}},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.58.834},
year = {2003}
}
@inproceedings{Pesek2014,
address = {Taipei},
author = {Pesek, Matev\v{z} and Godec, Primo\v{z}},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
title = {{INTRODUCING A DATASET OF EMOTIONAL AND COLOR RESPONSES TO MUSIC}},
year = {2014}
}
@book{Klapuri2006,
address = {New York},
editor = {Klapuri, Anssi and Davy, Manuel},
keywords = {Image and Speech Processing,Pattern Recognition,Signal,Signal Processing Methods for Music Transcription},
pages = {440},
publisher = {Springer},
title = {{Signal Processing Methods for Music Transcription}},
url = {http://www.springer.com/engineering/signals/book/978-0-387-30667-4},
year = {2006}
}
@inproceedings{Ni2012,
address = {Porto},
author = {Ni, Yizhao and McVicar, Matt and Santos-Rodriguez, Raul and Bie, Tijl De},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
pages = {109--114},
title = {{Using Hyper-genre Training to Explore Genre Information for Automatic Chord Estimation}},
year = {2012}
}
@inproceedings{Song2012,
address = {London},
author = {Song, Y and Dixon, S and Pearce, M},
booktitle = {Proc. 9th Int. Symp. Computer Music Modelling and Retrieval (CMMR)},
pages = {395--410},
title = {{A survey of music recommendation systems and future perspectives}},
year = {2012}
}
@inproceedings{Mauch2010,
address = {Utrecht},
author = {Mauch, Matthias and Dixon, Simon},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
title = {{Approximate Note Transcription For The Improved Identification Of Difficult Chords}},
year = {2010}
}
@article{Felleman1991,
author = {Felleman, Daniel J and {Van Essen}, David C},
journal = {Cerebral Cortex},
number = {1},
pages = {1--47},
title = {{Distributed Hierarchical Processing in the Primate Cerebral Cortex}},
volume = {1},
year = {1991}
}
@article{Meredith2002,
abstract = {In previous approaches to repetition discovery in music, the music to be analysed has been represented using strings. However, there are certain types of interesting musical repetitions that cannot be discovered using string algorithms. We propose a geometric approach to repetition discovery in which the music is represented as a multidimensional dataset. Certain types of interesting musical repetition that cannot be found using string algorithms can efficiently be found using algorithms that process multidimensional datasets. Our approach allows polyphonic music to be analysed as efficiently as monophonic music and it can be used to discover polyphonic repeated patterns ?with gaps? in the timbre, dynamic and rhythmic structure of a passage as well as its pitch structure. We present two new algorithms: SIA and SIATEC. SIA computes all the maximal repeated patterns in a multidimensional dataset and SIATEC computes all the occurrences of all the maximal repeated patterns in a dataset. For a k -dimensional dataset of size n, the worstcase running time of SIA is O (kn 2 log 2 n) and the worst-case running time of SIATEC is O (kn 3). In previous approaches to repetition discovery in music, the music to be analysed has been represented using strings. However, there are certain types of interesting musical repetitions that cannot be discovered using string algorithms. We propose a geometric approach to repetition discovery in which the music is represented as a multidimensional dataset. Certain types of interesting musical repetition that cannot be found using string algorithms can efficiently be found using algorithms that process multidimensional datasets. Our approach allows polyphonic music to be analysed as efficiently as monophonic music and it can be used to discover polyphonic repeated patterns ?with gaps? in the timbre, dynamic and rhythmic structure of a passage as well as its pitch structure. We present two new algorithms: SIA and SIATEC. SIA computes all the maximal repeated patterns in a multidimensional dataset and SIATEC computes all the occurrences of all the maximal repeated patterns in a dataset. For a k -dimensional dataset of size n, the worstcase running time of SIA is O (kn 2 log 2 n) and the worst-case running time of SIATEC is O (kn 3).},
author = {Meredith, David and Lemstrom, Kjell and Wiggins, Geraint A},
doi = {10.1076/jnmr.31.4.321.14162},
issn = {0929-8215},
journal = {Journal of New Music Research},
month = dec,
number = {4},
pages = {321--345},
publisher = {Routledge},
title = {{Algorithms for discovering repeated patterns in multidimensional representations of polyphonic music}},
url = {http://www.tandfonline.com/doi/abs/10.1076/jnmr.31.4.321.14162},
volume = {31},
year = {2002}
}
@article{Remmington2000,
abstract = {The circumplex model of affect has been among the most widely studied representations of affect. Despite the considerable evidence cited in support of it, methods typically used to evaluate the model have substantial limitations. In this article, the authors attempt to correct past limitations by using a covariance structure model specifically designed to assess circumplex structure. This model was fit to 47 individual correlation matrices from published data sets. Analyses revealed that model fit was typically acceptable and that opposing affective states usually demonstrated strong negative correlations with one another. However, analyses also indicated substantial variability in both model fit and correlations among opposing affective states and suggested several characteristics of studies that partially accounted for this variability. Detailed examination of the locations of affective states for 10 of the correlation matrices with relatively optimal characteristics provided mixed support for the model.},
author = {Remmington, N A and Fabrigar, L R and Visser, P S},
issn = {0022-3514},
journal = {Journal of personality and social psychology},
keywords = { Psychological, Statistical,Affect,Confounding Factors (Epidemiology),Data Interpretation,Humans,Models},
number = {2},
pages = {286--300},
pmid = {10948981},
title = {{Reexamining the circumplex model of affect.}},
url = {http://www.ncbi.nlm.nih.gov/pubmed/10948981},
volume = {79},
year = {2000}
}
@article{turnbull2008semantic,
author = {Turnbull, Douglas and Barrington, Luke and Torres, David and Lanckriet, Gert},
journal = {Audio, Speech, and Language Processing, IEEE Transactions on},
number = {2},
pages = {467--476},
publisher = {IEEE},
title = {{Semantic annotation and retrieval of music and sound effects}},
volume = {16},
year = {2008}
}
@article{DavidA.2004,
author = {{David A.}, Schwartz and Purves, Dale},
journal = {Hearing Research},
number = {1-2},
pages = {31--46},
title = {{Pitch is determined by naturally occuring periodic sounds}},
year = {2004}
}
@inproceedings{Sheh2003,
address = {Baltimore},
author = {Sheh, Alexander and Ellis, Daniel},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
pages = {1--7},
title = {{Chord segmentation and recognition using EM-trained hidden Markov models}},
year = {2003}
}
@misc{Smith1983,
author = {Smith, Dave and Wood, Chet},
title = {{MIDI Musical Instrument Digital Interface Specification 1.0}},
year = {1983}
}
@book{Rokach2007,
author = {Rokach, Lior and Maimon, Oded Z},
pages = {244},
publisher = {World Scientific Publishing},
title = {{Data Mining with Decision Trees: Theory and Applications}},
year = {2007}
}
@inproceedings{Schmidt2011,
abstract = {The medium of music has evolved specifically for the expression of emotions, and it is natural for us to organize music in terms of its emotional associations. But while such organization is a natural process for humans, quantifying it empirically proves to be a very difficult task, and as such no dominant feature representation for music emotion recognition has yet emerged. Much of the difficulty in developing emotion-based features is the ambiguity of the ground-truth. Even using the smallest time window, opinions on the emotion are bound to vary and reflect some disagreement between listeners. In previous work, we have modeled human response labels to music in the arousal-valence (A-V) representation of affect as a time-varying, stochastic distribution. Current methods for automatic detection of emotion in music seek performance increases by combining several feature domains (e.g. loudness, timbre, harmony, rhythm). Such work has focused largely in dimensionality reduction for minor classification performance gains, but has provided little insight into the relationship between audio and emotional associations. In this new work we seek to employ regression-based deep belief networks to learn features directly from magnitude spectra. While the system is applied to the specific problem of music emotion recognition, it could be easily applied to any regression-based audio feature learning problem.},
author = {Schmidt, Erik M and Kim, Youngmoo E},
booktitle = {2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
doi = {10.1109/ASPAA.2011.6082328},
isbn = {978-1-4577-0693-6},
issn = {1931-1168},
pages = {65--68},
publisher = {IEEE},
shorttitle = {Applications of Signal Processing to Audio and Aco},
title = {{Learning emotion-based acoustic features with deep belief networks}},
url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6082328},
year = {2011}
}
@article{abdi2007method,
author = {Abdi, Herv\'{e}},
journal = {Encyclopedia of Measurement and Statistics. CA, USA: Thousand Oaks},
title = {{The method of least squares}},
year = {2007}
}
@article{Emiya2010,
abstract = {A new method for the estimation of multiple concurrent pitches in piano recordings is presented. It addresses the issue of overlapping overtones by modeling the spectral envelope of the overtones of each note with a smooth autoregressive model. For the background noise, a moving-average model is used and the combination of both tends to eliminate harmonic and sub-harmonic erroneous pitch estimations. This leads to a complete generative spectral model for simultaneous piano notes, which also explicitly includes the typical deviation from exact harmonicity in a piano overtone series. The pitch set which maximizes an approximate likelihood is selected from among a restricted number of possible pitch combinations as the one. Tests have been conducted on a large homemade database called MAPS, composed of piano recordings from a real upright piano and from high-quality samples.},
author = {Emiya, Valentin and Badeau, Roland and David, Bertrand},
doi = {10.1109/TASL.2009.2038819},
issn = {1558-7916},
journal = {IEEE Transactions on Audio, Speech, and Language Processing},
keywords = {Acoustic signal analysis,MAPS,acoustic signal processing,audio processing,autoregressive processes,homemade database,moving-average model,multipitch estimation,multipitch estimation (MPE),musical instruments,overlapping overtones,piano,piano overtone series,piano recordings,piano sounds,probabilistic spectral smoothness principle,probability,smooth autoregressive model,smoothing methods,spectral analysis,spectral envelope modeling,spectral smoothness,transcription},
number = {6},
pages = {1643--1654},
shorttitle = {Audio, Speech, and Language Processing, IEEE Trans},
title = {{Multipitch Estimation of Piano Sounds Using a New Probabilistic Spectral Smoothness Principle}},
url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5356234},
volume = {18},
year = {2010}
}
@article{Oudre2011,
author = {Oudre, Laurent and Grenier, Yves and Fevotte, Cedric},
journal = {IEEE Transactions on Audio, Speech, and Language Processing},
number = {7},
pages = {2222--2233},
title = {{Chord Recognition by Fitting Rescaled Chroma Vectors to Chord Templates}},
volume = {19},
year = {2011}
}
@article{Leonardis2007,
author = {Leonardis, Ale\v{s} and Fidler, Sanja},
journal = {Computer Vision and Pattern Recognition, IEEE},
pages = {1--8},
title = {{Towards scalable representations of object categories: Learning a hierarchy of parts}},
year = {2007}
}
@inproceedings{mauch:adt:2013,
author = {Mauch, Matthias and Ewert, Sebastian},
booktitle = {Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR 2013)},
pages = {83--88},
title = {{The \{A\}udio \{D\}egradation \{T\}oolbox and its Application to Robustness Evaluation}},
year = {2013}
}
@incollection{Scherer2001,
address = {New York},
author = {Scherer, K R and Zentner, M R},
booktitle = {Music and emotion},
editor = {Juslin, P N and Sloboda, J A},
publisher = {Oxford University Press},
title = {{Emotional effects of music: production rules}},
year = {2001}
}
@article{Laskowski1979,
author = {Laskowski, Larry},
journal = {Journal of Music Theory},
number = {2},
pages = {304--307},
title = {{Heinrich Schenker: An Annotated Index to His Analyses of Musical Works}},
volume = {23},
year = {1979}
}
@article{Lewis2013,
author = {Lewis, James R},
journal = {Interacting with computers},
number = {4},
pages = {320--324},
title = {{Critical Review of ‘The Usability Metric for User Experience’}},
volume = {25},
year = {2013}
}
@article{Salamon2014,
abstract = {Melody extraction algorithms aim to produce a sequence of frequency values corresponding to the pitch of the dominant melody from a musical recording. Over the past decade, melody extraction has emerged as an active research topic, comprising a large variety of proposed algorithms spanning a wide range of techniques. This article provides an overview of these techniques, the applications for which melody extraction is useful, and the challenges that remain. We start with a discussion of ?melody? from both musical and signal processing perspectives and provide a case study that interprets the output of a melody extraction algorithm for specific excerpts. We then provide a comprehensive comparative analysis of melody extraction algorithms based on the results of an international evaluation campaign. We discuss issues of algorithm design, evaluation, and applications that build upon melody extraction. Finally, we discuss some of the remaining challenges in melody extraction research in terms of algorithmic performance, development, and evaluation methodology.},
author = {Salamon, Justin and Gomez, Emilia and Ellis, Daniel P W and Richard, Gael},
doi = {10.1109/MSP.2013.2271648},
issn = {1053-5888},
journal = {IEEE Signal Processing Magazine},
number = {2},
pages = {118--134},
shorttitle = {Signal Processing Magazine, IEEE},
title = {{Melody Extraction from Polyphonic Music Signals: Approaches, applications, and challenges}},
url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6739213},
volume = {31},
year = {2014}
}
@inproceedings{Gomez2004,
address = {Barcelona},
author = {Gomez, Emilia and Herrera, Perfecto},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
pages = {92--95},
title = {{Estimating the Tonality of Polyphonic Audio Files: Cognitive versus Machine Learning Modelling Strategies}},
year = {2004}
}
@inproceedings{AndrewJ.2010,
address = {Seattle},
author = {Milne, Andrew J},
booktitle = {Proceedings of International Conference of Music Perception and Cognition},
title = {{Tonal music theory: A psychoacoustic explanation?}},
year = {2010}
}
@inproceedings{Smith2011,
address = {Miami},
author = {Smith, Jordan B L and Burgoyne, J Ashley and Fujinaga, Ichiro and {De Roure}, David and Downie, J Stephen},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
number = {Ismir},
pages = {555--560},
title = {{Design and Creation of a Large-scale Database of Structural Annotations}},
year = {2011}
}
@inproceedings{Lee2009,
author = {Lee, Honglak and Pham, Peter and Largman, Yan and Ng, Andrew Y},
booktitle = {Advances in Neural Information Processing Systems},
pages = {1096--1104},
title = {{Unsupervised feature learning for audio classification using convolutional deep belief networks}},
url = {http://papers.nips.cc/paper/3674-unsupervised-feature-learning-for-audio-classification-using-convolutional-deep-belief-networks},
year = {2009}
}
@inproceedings{schmidt2011modeling,
author = {Schmidt, Erik M and Kim, Youngmoo E},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
pages = {777--782},
title = {{Modeling Musical Emotion Dynamics with Conditional Random Fields.}},
year = {2011}
}
@inproceedings{Laurier2009a,
author = {Laurier, Cyril and Lartillot, Olivier and Eerola, Tuomas and Toiviainen, Petri},
booktitle = {Proceedings of the Conference of European Society for the Cognitive Sciences of Music (ESCOM)},
title = {{Exploring Relationships between Audio Features and Emotion in Music}},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.182.728},
year = {2009}
}
@inproceedings{Schluter2013,
author = {Schluter, Jan and Bock, Sebastian},
booktitle = {6th International Workshop on Machine Learning and Music, held in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML/PKDD 2013},
title = {{Musical Onset Detection with Convolutional Neural Networks}},
year = {2013}
}
@inproceedings{Dessein2010,
author = {Dessein, A and Cont, A and Lemaitre, G},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
pages = {489--494},
title = {{Real-time polyphonic music transcription with non-negative matrix factorization and beta-divergence}},
url = {http://hal.upmc.fr/hal-00708682},
year = {2010}
}
@book{Bregman1990,
author = {Bregman, Albert S},
pages = {773},
publisher = {MIT Press},
title = {{Auditory scene analysis - The perceptual organization of sound}},
year = {1990}
}
@inproceedings{Battenberg2012,
author = {Battenberg, Eric and Wessel, David},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
pages = {37--42},
title = {{Analyzing Drum Patterns using Conditional Deep Belief Networks}},
year = {2012}
}
@article{Balaguer-Ballester2009,
author = {Balaguer-Ballester, Emili and Clark, Nicolas R and Coath, Martin and Krumbholz, Katrin and Denham, Susan L},
journal = {PLoS Computational Biology},
number = {3},
pages = {1--15},
title = {{Understanding Pitch Perception as a Hierarchical Process with Top-Down Modulation}},
volume = {4},
year = {2009}
}
@article{Cooper2006,
author = {Cooper, Matthew and Foote, Jonathan and Pampalk, Elias and Tzanetakis, George},
journal = {Computer music journal},
number = {2},
pages = {42--62},
title = {{Visualization in Audio-Based Music Information Retrieval}},
volume = {30},
year = {2006}
}
@book{Palm1986,
address = {Berlin, Heidelberg},
doi = {10.1007/978-3-642-70911-1},
editor = {Palm, G\"{u}nther and Aertsen, Ad},
isbn = {978-3-642-70913-5},
publisher = {Springer Berlin Heidelberg},
title = {{Brain Theory}},
url = {http://www.springerlink.com/index/10.1007/978-3-642-70911-1},
year = {1986}
}
@book{Werner2012,
address = {New York},
author = {Werner, Lynne A and Abdala, Carolina and Keefe, Douglas H and Eggermont, Jos J and Moore, Jean K and Buss, Emily and Hall, Joseph W I I I and Grose, John H and Leibold, Lori J and Litovsky, Ruth Y and Panneton, Robin and Newman, Rochelle and Trainor, Laurel J and Unrau, Andrea and Eisenberg, Laurie S and Johnson, Karen C and Ambrose, Sophie E},
editor = {Jones, Mari Riess and Fay, Richard R and Popper, Arthur N},
pages = {284},
publisher = {Springer},
title = {{Human Auditory Development}},
year = {2012}
}
@inproceedings{Mauch2008,
address = {Philadelphia},
author = {Mauch, Mathias and Dixon, Simon},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
pages = {45--50},
title = {{A Discrete Mixture Model for Chord Labelling}},
volume = {1},
year = {2008}
}
@inproceedings{mauch:adt:2013,
author = {Mauch, Matthias and Ewert, Sebastian},
booktitle = {Proceedings of the 14th International Society for Music Information Retrieval Conference (ISMIR 2013)},
pages = {83--88},
title = {{The Audio Degradation Toolbox and its Application to Robustness Evaluation}},
year = {2013}
}
@article{Mohamed2010,
author = {Mohamed, Abdel-rahman and Dahl, George E and Hinton, Geoffrey},
journal = {IEEE Transactions on Audio, Speech, and Language Processing},
number = {1},
pages = {14--22},
title = {{Acoustic Modeling using Deep Belief Networks}},
volume = {20},
year = {2010}
}
@article{Beeli2007,
author = {Beeli, Gian and Esslen, Michaela and Jancke, Lutz},
journal = {Psychological Science},
number = {9},
pages = {788--792},
title = {{Frequency Correlates in Grapheme-Color Synaesthesia}},
volume = {18},
year = {2007}
}
@inproceedings{Humphrey2012,
address = {Porto},
author = {Humphrey, Eric J and Bello, Juan P and LeCun, Yann},
booktitle = {Proceedings of the International Conference on Music Information Retrieval (ISMIR)},
title = {{Moving beyond feature design: deep architectures and automatic feature learning in music informatics}},
year = {2012}
}
@article{Lee2008,
author = {Lee, Kyogu and Stanley, Malcom},
journal = {IEEE Transactions on Audio, Speech, and Language Processing},
number = {2},
pages = {291--301},
title = {{Acoustic Chord Transcription and Key Extraction From Audio Using Key-Dependent HMMs Trained on Synthesized Audio}},
volume = {16},
year = {2008}
}
@inproceedings{Mauch2007,
address = {Vienna},
author = {Mauch, Matthias and Dixon, Simon and Harte, Christopher},