asr.bib

   1
   2 @article{yang_machine_2012,
   3         title = {Machine {Recognition} of {Music} {Emotion}: {A} {Review}},
   4         volume = {3},
   5         issn = {21576904},
   6         shorttitle = {Machine {Recognition} of {Music} {Emotion}},
   7         url = {http://dl.acm.org/citation.cfm?doid=2168752.2168754},
   8         doi = {10.1145/2168752.2168754},
   9         language = {en},
  10         number = {3},
  11         urldate = {2017-03-02},
  12         journal = {ACM Transactions on Intelligent Systems and Technology},
  13         author = {Yang, Yi-Hsuan and Chen, Homer H.},
  14         month = may,
  15         year = {2012},
  16         pages = {1--30},
  17         file = {TST00040.dvi - a40-yang.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/RGP3XNGT/a40-yang.pdf:application/pdf}
  18 }
  19
  20 @article{dzhambazov_automatic_2016,
  21         title = {Automatic {Alignment} of {Long} {Syllables} in a {Cappella} {Beijing} {Opera}},
  22         url = {http://arrow.dit.ie/fema/1/},
  23         urldate = {2017-03-02},
  24         author = {Dzhambazov, Georgi and Yang, Yile and Repetto, Rafael Caro and Serra, Xavier},
  25         year = {2016},
  26         file = {Automatic Alignment of Long Syllables in a Cappella Beijing Opera - viewcontent.cgi:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/CSCH3FAK/viewcontent.pdf:application/pdf}
  27 }
  28
  29 @inproceedings{dzhambazov_automatic_2014,
  30         title = {Automatic lyrics-to-audio alignment in classical turkish music},
  31         url = {http://www.academia.edu/download/46199701/lyrics-to-audio-FMA_full_paper.pdf},
  32         urldate = {2017-03-02},
  33         booktitle = {The 4th {International} {Workshop} on {Folk} {Music} {Analysis}},
  34         author = {Dzhambazov, Georgi and Sentürk, Sertan and Serra, Xavier},
  35         year = {2014},
  36         pages = {61--64},
  37         file = {lyrics-to-audio-FMA_full_paper.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/K7WFQSR8/lyrics-to-audio-FMA_full_paper.pdf:application/pdf}
  38 }
  39
  40 @inproceedings{kato_acoustic_2013,
  41         title = {Acoustic {Features} and {Auditory} {Impressions} of {Death} {Growl} and {Screaming} {Voice}},
  42         isbn = {978-0-7695-5120-3},
  43         url = {http://ieeexplore.ieee.org/document/6846676/},
  44         doi = {10.1109/IIH-MSP.2013.120},
  45         urldate = {2017-04-11},
  46         publisher = {IEEE},
  47         author = {Kato, Keizo and Ito, Akinori},
  48         month = oct,
  49         year = {2013},
  50         pages = {460--463},
  51         file = {Acoustic Features and Auditory Impressions of Death Growl and Screaming Voice - 06846676.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/VAT5AGPP/06846676.pdf:application/pdf}
  52 }
  53
  54 @article{boersma_praat_2002,
  55         title = {Praat, a system for doing phonetics by computer},
  56         volume = {5},
  57         journal = {Glot international},
  58         author = {Boersma, Paulus Petrus Gerardus},
  59         year = {2002}
  60 }
  61
  62 @inproceedings{leglaive_singing_2015,
  63         title = {Singing voice detection with deep recurrent neural networks},
  64         url = {http://ieeexplore.ieee.org/abstract/document/7177944/},
  65         urldate = {2017-04-25},
  66         booktitle = {Acoustics, {Speech} and {Signal} {Processing} ({ICASSP}), 2015 {IEEE} {International} {Conference} on},
  67         publisher = {IEEE},
  68         author = {Leglaive, Simon and Hennequin, Romain and Badeau, Roland},
  69         year = {2015},
  70         pages = {121--125},
  71         file = {SINGING VOICE DETECTION WITH DEEP RECURRENT NEURAL NETWORKS - 07177944.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/5K4JZDXC/07177944.pdf:application/pdf}
  72 }
  73
  74 @book{tsatsishvili_automatic_2011,
  75         title = {Automatic subgenre classification of heavy metal music},
  76         url = {https://jyx.jyu.fi/dspace/handle/123456789/37227},
  77         urldate = {2017-03-06},
  78         author = {Tsatsishvili, Valeri},
  79         year = {2011},
  80         file = {AUTOMATIC-SUBGENRE-CLASSIFICATION-OF-HEAVY-METAL-MUSIC.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/3HTFFPVN/AUTOMATIC-SUBGENRE-CLASSIFICATION-OF-HEAVY-METAL-MUSIC.pdf:application/pdf}
  81 }
  82
  83 @article{mauch_integrating_2012,
  84         title = {Integrating {Additional} {Chord} {Information} {Into} {HMM}-{Based} {Lyrics}-to-{Audio} {Alignment}},
  85         volume = {20},
  86         issn = {1558-7916},
  87         url = {http://ieeexplore.ieee.org/document/5876304/},
  88         doi = {10.1109/TASL.2011.2159595},
  89         number = {1},
  90         urldate = {2017-03-02},
  91         journal = {IEEE Transactions on Audio, Speech, and Language Processing},
  92         author = {Mauch, M. and Fujihara, H. and Goto, M.},
  93         month = jan,
  94         year = {2012},
  95         pages = {200--210},
  96         file = {untitled - 05876304.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/MM4NI9SJ/05876304.pdf:application/pdf}
  97 }
  98
  99 @inproceedings{saunders_real-time_1996,
 100         title = {Real-time discrimination of broadcast speech/music},
 101         volume = {2},
 102         booktitle = {Acoustics, {Speech}, and {Signal} {Processing}, 1996. {ICASSP}-96. {Conference} {Proceedings}., 1996 {IEEE} {International} {Conference} on},
 103         publisher = {IEEE},
 104         author = {Saunders, John},
 105         year = {1996},
 106         pages = {993--996},
 107         file = {REAL-TIME DISCRIMINATION OF BROADCAST SPEECH/MUSIC - Acoustics, Speech, and Signal Processing, 1996. ICASSP-96. Conference Proceedings., 1996 IEEE Inte - saunders_j2.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/H9PG94BN/saunders_j2.pdf:application/pdf}
 108 }
 109
 110 @inproceedings{nwe_singing_2004,
 111         title = {Singing voice detection in popular music},
 112         url = {http://dl.acm.org/citation.cfm?id=1027602},
 113         urldate = {2017-04-25},
 114         booktitle = {Proceedings of the 12th annual {ACM} international conference on {Multimedia}},
 115         publisher = {ACM},
 116         author = {Nwe, Tin Lay and Shenoy, Arun and Wang, Ye},
 117         year = {2004},
 118         pages = {324--327},
 119         file = {p324-nwe.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/HD48B4K8/p324-nwe.pdf:application/pdf}
 120 }
 121
 122 @article{you_comparative_2015,
 123         title = {Comparative study of singing voice detection methods},
 124         issn = {1380-7501, 1573-7721},
 125         url = {http://link.springer.com/10.1007/s11042-015-2894-9},
 126         doi = {10.1007/s11042-015-2894-9},
 127         language = {en},
 128         urldate = {2017-03-06},
 129         journal = {Multimedia Tools and Applications},
 130         author = {You, Shingchern D. and Wu, Yi-Chung and Peng, Shih-Hsien},
 131         month = aug,
 132         year = {2015},
 133         file = {11042_2015_2894_Article 1..16 - you2015.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/QQIS2H44/you2015.pdf:application/pdf}
 134 }
 135
 136 @inproceedings{fujihara_automatic_2006,
 137         title = {Automatic synchronization between lyrics and music {CD} recordings based on {Viterbi} alignment of segregated vocal signals},
 138         url = {http://ieeexplore.ieee.org/abstract/document/4061176/},
 139         urldate = {2017-03-02},
 140         booktitle = {Multimedia, 2006. {ISM}'06. {Eighth} {IEEE} {International} {Symposium} on},
 141         publisher = {IEEE},
 142         author = {Fujihara, Hiromasa and Goto, Masataka and Ogata, Jun and Komatani, Kazunori and Ogata, Tetsuya and Okuno, Hiroshi G.},
 143         year = {2006},
 144         pages = {257--264},
 145         file = {04061176.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/6DU997E4/04061176.pdf:application/pdf}
 146 }
 147
 148 @incollection{muller_lyrics--audio_2012,
 149         address = {Wadern},
 150         title = {Lyrics-to-{Audio} {Alignment} and its {Application}},
 151         isbn = {978-3-939897-37-8},
 152         url = {http://nbn-resolving.de/urn:nbn:de:0030-drops-27851},
 153         language = {English},
 154         urldate = {2017-03-02},
 155         booktitle = {Multimodal {Music} {Processing}},
 156         publisher = {Schloss Dagstuhl - Leibniz-Zentrum für Informatik GmbH},
 157         author = {Goto, Masataka and Fujihara, Hiromasa},
 158         editor = {Müller, Meinard},
 159         year = {2012},
 160         note = {OCLC: 864001691},
 161         pages = {23--36},
 162         file = {3.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/A4ZSSMW5/3.pdf:application/pdf}
 163 }
 164
 165 @inproceedings{scheirer_construction_1997,
 166         title = {Construction and evaluation of a robust multifeature speech/music discriminator},
 167         volume = {2},
 168         booktitle = {Acoustics, {Speech}, and {Signal} {Processing}, 1997. {ICASSP}-97., 1997 {IEEE} {International} {Conference} on},
 169         publisher = {IEEE},
 170         author = {Scheirer, Eric and Slaney, Malcolm},
 171         year = {1997},
 172         pages = {1331--1334}
 173 }
 174
 175 @inproceedings{mesaros_adaptation_2009,
 176         title = {Adaptation of a speech recognizer for singing voice},
 177         url = {http://ieeexplore.ieee.org/abstract/document/7077626/},
 178         urldate = {2017-03-02},
 179         booktitle = {Signal {Processing} {Conference}, 2009 17th {European}},
 180         publisher = {IEEE},
 181         author = {Mesaros, Annamaria and Virtanen, Tuomas},
 182         year = {2009},
 183         pages = {1779--1783},
 184         file = {07077626.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/FN9TWMMJ/07077626.pdf:application/pdf}
 185 }
 186
 187 @inproceedings{fujihara_three_2008,
 188         title = {Three techniques for improving automatic synchronization between music and lyrics: {Fricative} detection, filler model, and novel feature vectors for vocal activity detection},
 189         shorttitle = {Three techniques for improving automatic synchronization between music and lyrics},
 190         url = {http://ieeexplore.ieee.org/abstract/document/4517548/},
 191         urldate = {2017-03-02},
 192         booktitle = {Acoustics, {Speech} and {Signal} {Processing}, 2008. {ICASSP} 2008. {IEEE} {International} {Conference} on},
 193         publisher = {IEEE},
 194         author = {Fujihara, Hiromasa and Goto, Masataka},
 195         year = {2008},
 196         pages = {69--72},
 197         file = {THREE TECHNIQUES FOR IMPROVING AUTOMATIC SYNCHRONIZATION BETWEEN MUSIC AND LYRICS\: FRICATIVE DETECTION, FILLER MODEL, AND NOVEL FEATURE VECTORS FOR VOCAL ACTIVITY DETECTION - 04517548.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/CMGJ32AM/04517548.pdf:application/pdf}
 198 }
 199
 200 @inproceedings{berenzweig_locating_2001,
 201         title = {Locating singing voice segments within music signals},
 202         url = {http://ieeexplore.ieee.org/abstract/document/969557/},
 203         urldate = {2017-03-02},
 204         booktitle = {Applications of {Signal} {Processing} to {Audio} and {Acoustics}, 2001 {IEEE} {Workshop} on the},
 205         publisher = {IEEE},
 206         author = {Berenzweig, Adam L. and Ellis, Daniel PW},
 207         year = {2001},
 208         pages = {119--122},
 209         file = {Locating singing voice segments within music signals - Applicationis of Signal Processing to Audio and Acoustics, 2001 IEEE Workshop on the - 00969557.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/DWBBQPDE/00969557.pdf:application/pdf}
 210 }
 211
 212 @misc{friis_vikings_2004,
 213         title = {Vikings and their {Music}},
 214         url = {http://www.viking.no/e/life/music/e-musikk-mogens.html},
 215         urldate = {2017-04-11},
 216         author = {Friis, Mogens},
 217         year = {2004},
 218         file = {Vikings and their Music:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/SEEXI3VR/e-musikk-mogens.html:text/html}
 219 }
 220
 221 @inproceedings{sakakibara_growl_2004,
 222         title = {Growl voice in ethnic and pop styles},
 223         url = {http://www.overtone.cc/profiles/blogs/884327:BlogPost:7416},
 224         urldate = {2017-04-11},
 225         booktitle = {Proc. {Int}. {Symp}. on {Musical} {Acoustics}},
 226         author = {Sakakibara, K. and Fuks, Leonardo and Imagawa, Hiroshi and Tayama, Niro and Naganuma, D.},
 227         year = {2004},
 228         file = {isma04.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/PUFH652B/isma04.pdf:application/pdf}
 229 }
 230
 231 @inproceedings{vembu_separation_2005,
 232         title = {Separation of {Vocals} from {Polyphonic} {Audio} {Recordings}.},
 233         url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.139.5510&rep=rep1&type=pdf},
 234         urldate = {2017-04-25},
 235         booktitle = {{ISMIR}},
 236         publisher = {Citeseer},
 237         author = {Vembu, Shankar and Baumann, Stephan},
 238         year = {2005},
 239         pages = {337--344},
 240         file = {ismir05.dvi - download:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/WZ7INPRU/download.pdf:application/pdf}
 241 }
 242
 243 @inproceedings{pedone_phoneme-level_2011,
 244         title = {Phoneme-{Level} {Text} to {Audio} {Synchronization} on {Speech} {Signals} with {Background} {Music}.},
 245         url = {http://ai2-s2-pdfs.s3.amazonaws.com/7fb2/210b6a9e69ea7ca0e4f496548544781c8a8b.pdf},
 246         urldate = {2017-03-02},
 247         booktitle = {{INTERSPEECH}},
 248         author = {Pedone, Agnes and Burred, Juan José and Maller, Simon and Leveau, Pierre},
 249         year = {2011},
 250         pages = {433--436},
 251         file = {210b6a9e69ea7ca0e4f496548544781c8a8b.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/NQR3WB2S/210b6a9e69ea7ca0e4f496548544781c8a8b.pdf:application/pdf}
 252 }
 253
 254 @inproceedings{mesaros_automatic_2008,
 255         title = {Automatic alignment of music audio and lyrics},
 256         url = {http://legacy.spa.aalto.fi/dafx08/papers/dafx08_57.pdf},
 257         urldate = {2017-03-02},
 258         booktitle = {Proceedings of the 11th {Int}. {Conference} on {Digital} {Audio} {Effects} ({DAFx}-08)},
 259         author = {Mesaros, Annamaria and Virtanen, Tuomas},
 260         year = {2008},
 261         file = {dafx08_57.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/H24VX8KW/dafx08_57.pdf:application/pdf}
 262 }
 263
 264 @article{mesaros_automatic_2010,
 265         title = {Automatic {Recognition} of {Lyrics} in {Singing}},
 266         volume = {2010},
 267         issn = {1687-4714, 1687-4722},
 268         url = {http://asmp.eurasipjournals.com/content/2010/1/546047},
 269         doi = {10.1155/2010/546047},
 270         language = {en},
 271         urldate = {2017-03-02},
 272         journal = {EURASIP Journal on Audio, Speech, and Music Processing},
 273         author = {Mesaros, Annamaria and Virtanen, Tuomas},
 274         year = {2010},
 275         pages = {1--11},
 276         file = {art%3A10.1155%2F2010%2F546047.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/3BR5E733/art%3A10.1155%2F2010%2F546047.pdf:application/pdf}
 277 }
 278
 279 @article{fujihara_lyricsynchronizer:_2011,
 280         title = {{LyricSynchronizer}: {Automatic} {Synchronization} {System} {Between} {Musical} {Audio} {Signals} and {Lyrics}},
 281         volume = {5},
 282         issn = {1932-4553, 1941-0484},
 283         shorttitle = {{LyricSynchronizer}},
 284         url = {http://ieeexplore.ieee.org/document/5876296/},
 285         doi = {10.1109/JSTSP.2011.2159577},
 286         number = {6},
 287         urldate = {2017-03-02},
 288         journal = {IEEE Journal of Selected Topics in Signal Processing},
 289         author = {Fujihara, Hiromasa and Goto, Masataka and Ogata, Jun and Okuno, Hiroshi G.},
 290         month = oct,
 291         year = {2011},
 292         pages = {1252--1261},
 293         file = {untitled - 05876296.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/Q9MQTWHC/05876296.pdf:application/pdf}
 294 }
 295
 296 @inproceedings{sturm_survey_2012,
 297         title = {A survey of evaluation in music genre recognition},
 298         booktitle = {International {Workshop} on {Adaptive} {Multimedia} {Retrieval}},
 299         publisher = {Springer},
 300         author = {Sturm, Bob L},
 301         year = {2012},
 302         pages = {29--66},
 303         file = {Sturm20121212.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/6MJKTRHE/Sturm20121212.pdf:application/pdf}
 304 }
 305
 306 @inproceedings{williams_speech/music_1999,
 307         title = {Speech/music discrimination based on posterior probability features.},
 308         volume = {99},
 309         url = {https://pdfs.semanticscholar.org/1662/dba5ab1fc87e871605d1fc14b89b0b1a029c.pdf},
 310         urldate = {2017-05-16},
 311         booktitle = {Eurospeech},
 312         author = {Williams, Gethin and Ellis, Daniel PW},
 313         year = {1999},
 314         pages = {687--690},
 315         file = {euro99-uttclass.dvi - dba5ab1fc87e871605d1fc14b89b0b1a029c.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/PZDIDK4Q/dba5ab1fc87e871605d1fc14b89b0b1a029c.pdf:application/pdf}
 316 }
 317
 318 @inproceedings{berenzweig_using_2002,
 319         title = {Using voice segments to improve artist classification of music},
 320         url = {http://www.aes.org/e-lib/browse.cfm?elib=11147},
 321         urldate = {2017-05-16},
 322         booktitle = {Audio {Engineering} {Society} {Conference}: 22nd {International} {Conference}: {Virtual}, {Synthetic}, and {Entertainment} {Audio}},
 323         publisher = {Audio Engineering Society},
 324         author = {Berenzweig, Adam L. and Ellis, Daniel PW and Lawrence, Steve},
 325         year = {2002},
 326         file = {aes02-aclass.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/WJHA7NW6/aes02-aclass.pdf:application/pdf}
 327 }
 328
 329 @inproceedings{rocamora_comparing_2007,
 330         title = {Comparing audio descriptors for singing voice detection in music audio files},
 331         volume = {26},
 332         url = {https://pdfs.semanticscholar.org/b1c0/d8188b6459a47993c814f212556e02fcfc91.pdf},
 333         urldate = {2017-05-16},
 334         booktitle = {Brazilian symposium on computer music, 11th. san pablo, brazil},
 335         author = {Rocamora, Martın and Herrera, Perfecto},
 336         year = {2007},
 337         pages = {27},
 338         file = {sbcm2007Singing.dvi - d8188b6459a47993c814f212556e02fcfc91.pdf:/home/mrl/.mozilla/firefox/a614qfce.default/zotero/storage/3SMMC6VR/d8188b6459a47993c814f212556e02fcfc91.pdf:application/pdf}
 339 }