{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T06:21:54Z","timestamp":1768717314693,"version":"3.49.0"},"publisher-location":"Berlin, Heidelberg","reference-count":41,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642116735","type":"print"},{"value":"9783642116742","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-11674-2_15","type":"book-chapter","created":{"date-parts":[[2010,3,10]],"date-time":"2010-03-10T05:30:47Z","timestamp":1268199047000},"page":"333-363","source":"Crossref","is-referenced-by-count":7,"title":["Multimodal Aspects of Music Retrieval: Audio, Song Lyrics \u2013 and Beyond?"],"prefix":"10.1007","author":[{"given":"Rudolf","family":"Mayer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Rauber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"15_CR1","unstructured":"Allamanche, E., Herre, J., Hellmuth, O., Fr\u00f6ba, B., Kastner, T., Cremer, M.: Content-based identification of audio material using MPEG-7 low level description. In: Proceedings of the International Symposium on Music Information Retrieval (ISMIR), Bloomington, IN, USA, October 15-17, pp. 197\u2013204 (2001)"},{"key":"15_CR2","unstructured":"Aucouturier, J.-J., Pachet, F.: Improving timbre similarity: How high is the sky? Journal of Negative Results in Speech and Audio Sciences\u00a01(1) (2004)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Baumann, S., Pohle, T., Vembu, S.: Towards a socio-cultural compatibility of MIR systems. In: Proceedings of the 5th International Conference of Music Information Retrieval (ISMIR 2004), Barcelona, Spain, October 10-14, pp. 460\u2013465 (2004)","DOI":"10.1045\/december2004-droettboom"},{"key":"15_CR4","unstructured":"Brochu, E., de Freitas, N., Bao, K.: The sound of an album cover: Probabilistic multimedia and IR. In: Proceedings of the 9th International Workshop on Artificial Intelligence and Statistics, Key West, FL, USA, January 3-6 (2003)"},{"key":"15_CR5","unstructured":"Cavnar, W.B., Trenkle, J.M.: N-gram-based text categorization. In: Proceedings of the 3rd Annual Symposium on Document Analysis and Information Retrieval (SDAIR 1994), Las Vegas, USA, pp. 161\u2013175 (1994)"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Crysandt, H., Wellhausen, J.: Music classification with MPEG-7. In: Proceedings of SPIE-IS&T Electronic Imaging, Santa Clara (CA), USA, January 2003. Storage and Retrieval for Media Databases, vol.\u00a05021, pp. 307\u2013404. The International Society for Optical Engineering (2003)","DOI":"10.1117\/12.476257"},{"key":"15_CR7","first-page":"5","volume-title":"Proceedings of the 3rd ACM\/IEEE-CS joint conference on Digital libraries (JCDL 2003)","author":"S.J. Cunningham","year":"2003","unstructured":"Cunningham, S.J., Reeves, N., Britland, M.: An ethnographic study of music information seeking: implications for the design of a music digital library. In: Proceedings of the 3rd ACM\/IEEE-CS joint conference on Digital libraries (JCDL 2003), Washington, DC, USA, pp. 5\u201316. IEEE Computer Society, Los Alamitos (2003)"},{"key":"15_CR8","first-page":"295","volume-title":"Annual Review of Information Science and Technology","author":"J. Stephen Downie","year":"2003","unstructured":"Stephen Downie, J.: Music Information Retrieval. In: Annual Review of Information Science and Technology, vol.\u00a037, pp. 295\u2013340. Information Today, Medford (2003)"},{"issue":"6","key":"15_CR9","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1109\/TASSP.1976.1162873","volume":"24","author":"H.S. Elovitz","year":"1976","unstructured":"Elovitz, H.S., Johnson, R., McHugh, A., Shore, J.E.: Letter-to-sound rules for automatic translation of English text to phonetics. IEEE Transactions on Acoustics, Speech and Signal Processing\u00a024(6), 446\u2013459 (1976)","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing"},{"issue":"1","key":"15_CR10","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s005300050106","volume":"7","author":"J. Foote","year":"1999","unstructured":"Foote, J.: An overview of audio information retrieval. Multimedia Systems\u00a07(1), 2\u201310 (1999)","journal-title":"Multimedia Systems"},{"issue":"5","key":"15_CR11","doi-asserted-by":"publisher","first-page":"1783","DOI":"10.1109\/TSA.2005.863204","volume":"14","author":"M. Goto","year":"2006","unstructured":"Goto, M.: A chorus section detection method for musical audio signals and its application to a music listening station. IEEE Transactions on Audio, Speech & Language Processing\u00a014(5), 1783\u20131794 (2006)","journal-title":"IEEE Transactions on Audio, Speech & Language Processing"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Iskandar, D., Wang, Y., Kan, M.-Y., Li, H.: Syllabic level automatic synchronization of music signals and text lyrics. In: Proceedings of the ACM 14th International Conference on Multimedia (MM 2006), New York, NY, USA, pp. 659\u2013662(2006)","DOI":"10.1145\/1180639.1180777"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Knees, P., Schedl, M., Pohle, T., Widmer, G.: An Innovative Three-Dimensional User Interface for Exploring Music Collections Enriched with Meta-Information from the Web. In: Proceedings of the ACM 14th International Conference on Multimedia (MM2006), Santa Barbara, California, USA, October 23-26, pp. 17\u201324 (2006)","DOI":"10.1145\/1180639.1180652"},{"key":"15_CR14","unstructured":"Knees, P., Schedl, M., Widmer, G.: Multiple lyrics alignment: Automatic retrieval of song lyrics. In: Proceedings of 6th International Conference on Music Information Retrieval (ISMIR 2005), London, UK, September 11-15, pp. 564\u2013569 (2005)"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Laurier, C., Grivolla, J., Herrera, P.: Multimodal music mood classification using audio and lyrics. In: Proceedings of the Seventh International Conference on Machine Learning and Applications (ICMLA 2008), San Diego, CA, USA, December 11-13, pp. 688\u2013693 (2008)","DOI":"10.1109\/ICMLA.2008.96"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Li, T., Ogihara, M., Li, Q.: A comparative study on content-based music genre classification. In: Proceedings of the International ACM Conference on Research and Development in Information Retrieval (SIGIR), Toronto, Canada, pp. 282\u2013289 (2003)","DOI":"10.1145\/860435.860487"},{"key":"15_CR17","unstructured":"Lidy, T., Rauber, A.: Evaluation of feature extractors and psycho-acoustic transformations for music genre classification. In: Proceedings of the 6th International Conference on Music Information Retrieval (ISMIR 2005), London, UK, September 11-15, pp. 34\u201341 (2005)"},{"key":"15_CR18","unstructured":"Lidy, T., Rauber, A., Pertusa, A., Inesta, J.M.: Improving genre classification by combination of audio and symbolic descriptors using a transcription system. In: Proceedings of the International Conference on Music Information Retrieval (ISMIR), Vienna, Austria, September 23-27, pp. 61\u201366 (2007)"},{"key":"15_CR19","unstructured":"Logan, B.: Mel frequency cepstral coefficients for music modeling. In: Proceedings of the International Symposium on Music Information Retrieval (ISMIR), Plymouth, Massachusetts, USA, October 23-25 (2000)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Logan, B., Kositsky, A., Moreno, P.: Semantic analysis of song lyrics. In: Proceedings of the IEEE International Conference on Multimedia and Expo (ICME 2004), Taipei, Taiwan, June 27-30, pp. 827\u2013830 (2004)","DOI":"10.1109\/ICME.2004.1394328"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Logan, B., Salomon, A.: A music similarity function based on signal analysis. In: Proceedings of the IEEE International Conference on Multimedia and Expo (ICME), Tokyo, Japan (August 2001)","DOI":"10.1109\/ICME.2001.1237829"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Mahedero, J.P.G., Mart\u00ednez, \u00c1., Cano, P., Koppenberger, M., Gouyon, F.: Natural language processing of lyrics. In: Proceedings of the ACM 13th International Conference on Multimedia (MM 2005), New York, NY, USA, pp. 475\u2013478 (2005)","DOI":"10.1145\/1101149.1101255"},{"key":"15_CR23","first-page":"159","volume-title":"Proceedings of the ACM Multimedia 2008","author":"R. Mayer","year":"2008","unstructured":"Mayer, R., Neumayer, R., Rauber, A.: Combination of audio and lyrics features for genre classification in digital audio collections. In: Proceedings of the ACM Multimedia 2008, October 27-31, pp. 159\u2013168. ACM, New York (2008)"},{"key":"15_CR24","unstructured":"Mayer, R., Neumayer, R., Rauber, A.: Rhyme and style features for musical genre classification by song lyrics. In: Proceedings of the 9th International Conference on Music Information Retrieval (ISMIR 2008), Philadelphia, PA, USA, September 14-18 (2008)"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Neumayer, R., Rauber, A.: Integration of text and audio features for genre classification in music information retrieval. In: Proceedings of the 29th European Conference on Information Retrieval (ECIR 2007), pp. 724\u2013727, Rome, Italy, April 2-5 (2007)","DOI":"10.1007\/978-3-540-71496-5_78"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Neumayer, R., Rauber, A.: Multi-modal music information retrieval - visualisation and evaluation of clusterings by both audio and lyrics. In: Proceedings of the 8th Conference Recherche d\u2019Information Assist\u00e9e par Ordinateur (RIAO 2007), Pittsburgh, PA, USA, May 29th - June 1 (2007)","DOI":"10.1007\/978-0-387-76316-3_11"},{"issue":"1","key":"15_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/1500000002","volume":"1","author":"N. Orio","year":"2006","unstructured":"Orio, N.: Music retrieval: A tutorial and review. Foundations and Trends in Information Retrieval\u00a01(1), 1\u201390 (2006)","journal-title":"Foundations and Trends in Information Retrieval"},{"key":"15_CR28","unstructured":"Pampalk, E., Flexer, A., Widmer, G.: Hierarchical organization and description of music collections at the artist level. In: Proceedings of the 9th European Conference on Research and Advanced Technology for Digital Libraries (ECDL 2009) (2009)"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Pampalk, E., Rauber, A., Merkl, D.: Content-based Organization and Visualization of Music Archives. In: Proceedings of the ACM 10th International Conference on Multimedia (MM 2002), Juan les Pins, France, December 1-6, pp. 570\u2013579 (2002)","DOI":"10.1145\/641007.641121"},{"issue":"1","key":"15_CR30","first-page":"81","volume":"1","author":"J. Ross Quinlan","year":"1986","unstructured":"Ross Quinlan, J.: Induction of decision trees. Machine Learning\u00a01(1), 81\u2013106 (1986)","journal-title":"Machine Learning"},{"key":"15_CR31","volume-title":"Fundamentals of Speech Recognition","author":"L. Rabiner","year":"1993","unstructured":"Rabiner, L., Juang, B.-H.: Fundamentals of Speech Recognition. Prentice-Hall, Englewood Cliffs (1993)"},{"key":"15_CR32","unstructured":"Rauber, A., Pampalk, E., Merkl, D.: Using psycho-acoustic models and self-organizing maps to create a hierarchical structuring of music by musical styles. In: Proceedings of the 3rd International Symposium on Music Information Retrieval (ISMIR 2002), Paris, France, October 13-17, pp. 71\u201380 (2002)"},{"issue":"2","key":"15_CR33","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1076\/jnmr.32.2.193.16745","volume":"32","author":"A. Rauber","year":"2003","unstructured":"Rauber, A., Pampalk, E., Merkl, D.: The SOM-enhanced JukeBox: Organization and visualization of music collections based on perceptual models. Journal of New Music Research\u00a032(2), 193\u2013210 (2003)","journal-title":"Journal of New Music Research"},{"key":"15_CR34","volume-title":"Automatic text processing \u2013 The Transformation, Analysis, and Retrieval of Information by Computer","author":"G. Salton","year":"1989","unstructured":"Salton, G.: Automatic text processing \u2013 The Transformation, Analysis, and Retrieval of Information by Computer. Addison-Wesley Longman Publishing Co., Inc., Amsterdam (1989)"},{"issue":"12","key":"15_CR35","doi-asserted-by":"publisher","first-page":"2346","DOI":"10.1121\/1.1919362","volume":"36","author":"R.N. Shepard","year":"1964","unstructured":"Shepard, R.N.: Circularity in judgments of relative pitch. The Journal of the Acoustical Society of America\u00a036(12), 2346\u20132353 (1964)","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"30","key":"15_CR36","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1017\/S1355771800003071","volume":"4","author":"G. Tzanetakis","year":"2000","unstructured":"Tzanetakis, G., Cook, P.: Marsyas: A framework for audio analysis. Organized Sound\u00a04(30), 169\u2013175 (2000)","journal-title":"Organized Sound"},{"key":"15_CR37","doi-asserted-by":"crossref","unstructured":"Tzanetakis, G., Cook, P.: Sound analysis using MPEG compressed audio. In: Proceedings of the International Conference on Audio, Speech and Signal Processing (ICASSP), Istanbul, Turkey (2000)","DOI":"10.1109\/ICASSP.2000.859071"},{"issue":"5","key":"15_CR38","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TSA.2002.800560","volume":"10","author":"G. Tzanetakis","year":"2002","unstructured":"Tzanetakis, G., Cook, P.: Musical genre classification of audio signals. IEEE Transactions on Speech and Audio Processing\u00a010(5), 293\u2013302 (2002)","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"15_CR39","unstructured":"Xiong, Z., Radhakrishnan, R., Divakaran, A., Huang, T.S.: Comparing MFCC and MPEG-7 audio features for feature extraction, maximum likelihood HMM and entropic prior HMM for sports audio classification. In: Proceedings of the International Conference on Multimedia and Expo, ICME (2003)"},{"key":"15_CR40","unstructured":"Yang, D., Lee, W.: Disambiguating music emotion using software agents. In: Proceedings of the International Conference on Music Information Retrieval (ISMIR), Barcelona, Spain (October 2004)"},{"key":"15_CR41","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Chen, K., Sun, Q.: Multimodal content-based structure analysis of karaoke music. In: Proceedings of the ACM 13th International Conference on Multimedia (MM 2005), Singapore, pp. 638\u2013647 (2005)","DOI":"10.1145\/1101149.1101293"}],"container-title":["Studies in Computational Intelligence","Advances in Music Information Retrieval"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-11674-2_15.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T21:42:46Z","timestamp":1606167766000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-11674-2_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642116735","9783642116742"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-11674-2_15","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"value":"1860-949X","type":"print"},{"value":"1860-9503","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010]]}}}