{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T06:50:41Z","timestamp":1742799041655,"version":"3.32.0"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"4-5","license":[{"start":{"date-parts":[[2006,9,12]],"date-time":"2006-09-12T00:00:00Z","timestamp":1158019200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2007,2,8]]},"DOI":"10.1007\/s00530-006-0055-8","type":"journal-article","created":{"date-parts":[[2006,9,11]],"date-time":"2006-09-11T10:23:15Z","timestamp":1157970195000},"page":"307-323","source":"Crossref","is-referenced-by-count":15,"title":["Automatic lyrics alignment for Cantonese popular music"],"prefix":"10.1007","volume":"12","author":[{"given":"Chi Hang","family":"Wong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wai Man","family":"Szeto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kin Hong","family":"Wong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2006,9,12]]},"reference":[{"key":"55_CR1","doi-asserted-by":"crossref","unstructured":"Abdulla, W.H., Chow, D., Sin, G.: Cross-words reference template for dtw based speech recognition systems. In: IEEE TENCON, pp. 1576\u20131579 (2003)","DOI":"10.1109\/TENCON.2003.1273186"},{"key":"55_CR2","doi-asserted-by":"crossref","unstructured":"Berenzweig, A.L., Ellis, D.P.W.: Locating singing voice segments within music signals. In: IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, vol. W2001, pp. 1\u20134 (2001)","DOI":"10.1109\/ASPAA.2001.969557"},{"issue":"2","key":"55_CR3","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1109\/TASSP.1979.1163209","volume":"27","author":"S.F. Boll","year":"1979","unstructured":"Boll S.F. (1979): Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans Acoust Speech Signal Process ASSP 27(2): 113\u2013120","journal-title":"IEEE Trans Acoust Speech Signal Process ASSP"},{"key":"55_CR4","doi-asserted-by":"crossref","unstructured":"Chan, M.K.M.: Tone and melody in cantonese. In: Berkeley Linguistic Society, Proceedings of the Thirteenth Annual Meeting, pp. 26\u201337 (1987)","DOI":"10.3765\/bls.v13i0.1828"},{"issue":"4","key":"55_CR5","doi-asserted-by":"crossref","first-page":"1917","DOI":"10.1121\/1.1458024","volume":"111","author":"A. Cheveign\u00e9 de","year":"2002","unstructured":"de Cheveign\u00e9 A., Kawahara H. (2002): Yin, a fundamental frequency estimator for speech and music. J Acoust Soc Am 111(4): 1917\u20131930","journal-title":"J Acoust Soc Am"},{"key":"55_CR6","unstructured":"Chiang, Y.H., Fan, K., Kwan, T.W.: A chinese talking syllabary of the cantonese dialect. http:\/\/humanum.arts.cuhk. edu.hk\/lexis\/canton2\/"},{"key":"55_CR7","doi-asserted-by":"crossref","unstructured":"Chou, W., Gu, L.: Robust singing detection in speech\/music discriminator design. In: Proceedings of the ICASSP, pp. 865\u2013868 (2001)","DOI":"10.1109\/ICASSP.2001.941052"},{"key":"55_CR8","unstructured":"Clarisse, L.P., Martens, J.P., Lesaffre, M., De Baets, B., DeMeyer, H., Leman, M.: An auditory model based transcriber of singing sequences. In: Proceedings of the ISMIR, pp. 116\u2013123 (2002)"},{"key":"55_CR9","volume-title":"The Cambridge Encyclopedia of Language","author":"D. Crystal","year":"1997","unstructured":"Crystal D. (1997): The Cambridge Encyclopedia of Language, 2nd edn. Cambridge University Press, London","edition":"2"},{"key":"55_CR10","unstructured":"Dixon, S.: Live tracking of musical performances using on-line time warping. In: Proceedings of the 8th International Conference on Digital Audio Effects (DAFx05), pp. 92\u201397 (2005)"},{"key":"55_CR11","unstructured":"GoldWave Incorporated.: Goldwave version 5.06. http:\/\/www. goldwave.com"},{"key":"55_CR12","doi-asserted-by":"crossref","unstructured":"Hunt, J.M., Lenning, M., Mermelstein, P.: Experiments in syllable-based recognition of continuous speech. In: Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP \u201980, vol. 5, pp. 880\u2013883 (1980)","DOI":"10.1109\/ICASSP.1980.1170934"},{"key":"55_CR13","volume-title":"The Oxford Dictionary of Music","author":"M. Kennedy","year":"1994","unstructured":"Kennedy M. (1994): The Oxford Dictionary of Music, 2nd edn. Oxford University Press, New York","edition":"2"},{"key":"55_CR14","unstructured":"Klapuri, A.: Automatic transcription of music. Master\u2019s Thesis, Tampere University of Technology (1998)"},{"key":"55_CR15","unstructured":"Lawrence, S., Berenzweig, A., Ellis, D.P.W.: Using voice segments to improve artist classification of music. In: AES 22nd International Conference (2002)"},{"key":"55_CR16","doi-asserted-by":"crossref","unstructured":"Leung, T.-W., Ngo, C.-W., Lau, R.W.H.: Ica-fx features for classification of singing voice and instrumental sound. In: 17th International Conference on Pattern Recognition (ICPR\u201904), vol. 2, pp. 367\u2013370 (2004)","DOI":"10.1109\/ICPR.2004.1334222"},{"key":"55_CR17","unstructured":"Linguistic Society of Hong Kong.: Cantonese romanization. http:\/\/cpct92.cityu.edu.hk\/lshk\/"},{"key":"55_CR18","unstructured":"Loscos, A., Cano, P., Bonada, J.: Low-delay singing voice alignment to text. In: Proceedings of International Computer Music Conference (1999)"},{"key":"55_CR19","doi-asserted-by":"crossref","unstructured":"Lu, L., Jiang, H., Zhang, H.J.: A robust audio classification and segmentation method. In: Proceedings of the 9th ACM International Conference on Multimedia, pp. 203\u2013211 (2001)","DOI":"10.1145\/500141.500173"},{"key":"55_CR20","doi-asserted-by":"crossref","unstructured":"Maddage, N.C., Wan, K., Xu, C., Wang, Y.: Singing voice detection using twice-iterated composite fourier transform. In: 2004 IEEE International Conference on Multimedia and Expo (ICME), pp. 1347\u20131350 (2004)","DOI":"10.1109\/ICME.2004.1394478"},{"key":"55_CR21","doi-asserted-by":"crossref","unstructured":"Nwe, T.L., Shenoy, A., Wang, Y.: Singing voice detection in popular music. In: Proceedings of the 12th Annual ACM International Conference on Multimedia, pp. 324\u2013327 (2004)","DOI":"10.1145\/1027527.1027602"},{"key":"55_CR22","volume-title":"Mixing Engineer\u2019s Handbook","author":"B. Owsinski","year":"1999","unstructured":"Owsinski B. (1999): Mixing Engineer\u2019s Handbook. Thomson Course Technology, Boston"},{"key":"55_CR23","doi-asserted-by":"crossref","unstructured":"Pinquier, J., Rouas, J., Andr e Obrecht, R.: Robust speech\/ music classification in audio documents. In: International Conference on Spoken Language Processing, vol. 3, pp. 2005\u20132008 (2002)","DOI":"10.1109\/ICASSP.2002.1004854"},{"key":"55_CR24","unstructured":"Ryyn\u00e4nen, M.P., Klapuri, A.P.: Modelling of note events for singing transcription. In: Proceedings of the ISCA Tutorial and Research Workshop on Statistical and Perceptual Audio Processing (2004)"},{"key":"55_CR25","doi-asserted-by":"crossref","unstructured":"Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. In: IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. ASSP-26, pp. 43\u201349 (1978)","DOI":"10.1109\/TASSP.1978.1163055"},{"key":"55_CR26","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1121\/1.421129","volume":"1","author":"E.D. Scheirer","year":"1998","unstructured":"Scheirer E.D. (1998): Tempo and beat analysis of acoustic musical signals. J Acoust Soc Am 1, 588\u2013601","journal-title":"J Acoust Soc Am"},{"key":"55_CR27","doi-asserted-by":"crossref","unstructured":"Scheirer, E., Slaney, M.: Construction and evaluation of a robust multifeature speech\/music discriminator. In: Proceedings of the ICASSP, pp. 1331\u20131334 (1997)","DOI":"10.1109\/ICASSP.1997.596192"},{"key":"55_CR28","volume-title":"Advanced Signal Processing and Digital Noise Reduction","author":"S.V. Vaseghi","year":"2000","unstructured":"Vaseghi S.V. (2000): Advanced Signal Processing and Digital Noise Reduction. Wiley, New York"},{"key":"55_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Y., Kan, M.-Y., Nwe, T.L., Shenoy, A., Yin, J.: Lyrically: automatic synchronization of acoustic musical signals and textual lyrics. In: MULTIMEDIA \u201904: Proceedings of the 12th Annual ACM International Conference on Multimedia, pp. 212\u2013219 (2004)","DOI":"10.1145\/1027527.1027576"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-006-0055-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00530-006-0055-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-006-0055-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T20:25:43Z","timestamp":1736540743000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00530-006-0055-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,9,12]]},"references-count":29,"journal-issue":{"issue":"4-5","published-print":{"date-parts":[[2007,2,8]]}},"alternative-id":["55"],"URL":"https:\/\/doi.org\/10.1007\/s00530-006-0055-8","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2006,9,12]]}}}