{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T17:20:59Z","timestamp":1778347259176,"version":"3.51.4"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2013,6,27]],"date-time":"2013-06-27T00:00:00Z","timestamp":1372291200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/2.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J AUDIO SPEECH MUSIC PROC."],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1186\/1687-4722-2013-15","type":"journal-article","created":{"date-parts":[[2013,6,27]],"date-time":"2013-06-27T12:14:26Z","timestamp":1372335266000},"source":"Crossref","is-referenced-by-count":18,"title":["Reassigned spectrum-based feature extraction for GMM-based automatic chord recognition"],"prefix":"10.1186","volume":"2013","author":[{"given":"Maksim","family":"Khadkevich","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maurizio","family":"Omologo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,6,27]]},"reference":[{"key":"81_CR1","first-page":"239","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"JP Bello","year":"2007","unstructured":"Bello JP: Audio-based cover song retrieval using approximate chord sequences: testing shifts, gaps, swaps and beats. In Proceedings of the International Conference on Music Information Retrieval (ISMIR). Philadelphia; 2007:239-244."},{"key":"81_CR2","doi-asserted-by":"crossref","DOI":"10.1561\/9781601980717","volume-title":"Introduction to Digital Speech Processing","author":"LR Rabiner","year":"2007","unstructured":"Rabiner LR, Schafer RW: Now Publishers Inc. In Introduction to Digital Speech Processing. Hanover; 2007."},{"key":"81_CR3","first-page":"464","volume-title":"Proceedings of the International Computer Music Conference (ICMC)","author":"T Fujishima","year":"1999","unstructured":"Fujishima T: Realtime chord recognition of musical sound: a system using common lisp music. In Proceedings of the International Computer Music Conference (ICMC). Beijing; 1999:464-467."},{"key":"81_CR4","volume-title":"Proceedings of the International Symposium on Music Information Retrieval (ISMIR)","author":"A Sheh","year":"2003","unstructured":"Sheh A, Ellis DP: Chord segmentation and recognition using EM-trained hidden Markov models. In Proceedings of the International Symposium on Music Information Retrieval (ISMIR). Baltimore; 2003."},{"key":"81_CR5","first-page":"53","volume-title":"Proceedings of the International Workshop on Content-Based Multimedia Indexing (CBMI)","author":"H Papadopoulos","year":"2007","unstructured":"Papadopoulos H, Peeters G: Large-scale study of chord estimation algorithms based on chroma representation and HMM. In Proceedings of the International Workshop on Content-Based Multimedia Indexing (CBMI). Bordeaux; 2007:53-60."},{"key":"81_CR6","first-page":"45","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"M Mauch","year":"2008","unstructured":"Mauch M, Dixon S: A discrete mixture model for chord labelling. In Proceedings of the International Conference on Music Information Retrieval (ISMIR). Philadelphia; 2008:45-50."},{"key":"81_CR7","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1109\/TASL.2010.2045236","volume":"19","author":"H Papadopoulos","year":"2011","unstructured":"Papadopoulos H, Peeters G: Joint estimation of chords and downbeats from an audio signal. IEEE Trans. Audio, Speech, Lang, Process 2011, 19: 138-152.","journal-title":"IEEE Trans. Audio, Speech, Lang, Process"},{"key":"81_CR8","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"M M\u00fcller","year":"2011","unstructured":"M\u00fcller M, Ewert S: Chroma toolbox: MATLAB implementations for extracting variants of chroma-based audio features. In Proceedings of the International Conference on Music Information Retrieval (ISMIR). Miami; 2011."},{"key":"81_CR9","volume-title":"Proceedings of the 126th Convention of the Audio Engineering Society (AES)","author":"M Stein","year":"2009","unstructured":"Stein M, Schubert M, Gruhne BM, Gatzsche G, Mehnert M: Evaluation and comparison of audio chroma feature extraction methods. In Proceedings of the 126th Convention of the Audio Engineering Society (AES). Munich; 2009."},{"key":"81_CR10","first-page":"135","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"M Mauch","year":"2010","unstructured":"Mauch M, Dixon S: Approximate note transcription for the improved identification of difficult chords. In Proceedings of the International Conference on Music Information Retrieval (ISMIR). Utrecht; 2010:135-140."},{"key":"81_CR11","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1145\/1459359.1459455","volume-title":"Proceedings of the 16th ACM international conference on Multimedia","author":"M Varewyck","year":"2008","unstructured":"Varewyck M, Pauwels J, Martens JP: A novel chroma representation of polyphonic music based on multiple pitch tracking techniques. In Proceedings of the 16th ACM international conference on Multimedia. New York; 2008:667-670."},{"key":"81_CR12","first-page":"74","volume-title":"Proceedings of the 25th International AES Conference","author":"E G\u00f3mez","year":"2004","unstructured":"G\u00f3mez E, Herrera P: Automatic extraction of tonal metadata from polyphonic audio recordings. In Proceedings of the 25th International AES Conference. London; 2004:74-81."},{"key":"81_CR13","first-page":"5518","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Y Ueda","year":"2010","unstructured":"Ueda Y, Uchiyama Y, Nishimoto T, Ono N, Sagayama S: HMM-based approach for automatic chord detection using refined acoustic features. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Dallas; 2010:5518-5521."},{"issue":"2","key":"81_CR14","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1109\/TASL.2007.914399","volume":"16","author":"K Lee","year":"2008","unstructured":"Lee K, Slaney M: Acoustic chord transcription and key extraction from audio using key-dependent HMMs trained on synthesized audio. IEEE Trans. Audio, Speech, Lang. Process 2008, 16(2):291-301.","journal-title":"IEEE Trans. Audio, Speech, Lang. Process"},{"key":"81_CR15","first-page":"561","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"M Khadkevich","year":"2009","unstructured":"Khadkevich M, Omologo M: Use of hidden Markov models and factored language models for automatic chord recognition. In Proceedings of the International Conference on Music Information Retrieval (ISMIR). Kobe; 2009:561-566."},{"key":"81_CR16","first-page":"181","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"M Khadkevich","year":"2011","unstructured":"Khadkevich M, Omologo M: Time-frequency reassigned features for automatic chord recognition. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague; 2011:181-184."},{"key":"81_CR17","first-page":"141","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"T Rocher","year":"2010","unstructured":"Rocher T, Robine M, Hanna P, Oudre L: Concurrent estimation of chords and keys from audio. In Proceedings of the International Conference on Music Information Retrieval (ISMIR). Utrecht; 2010:141-146."},{"key":"81_CR18","volume-title":"Comput. Res. Repository (CoRR)","author":"KR Fitz","year":"2009","unstructured":"Fitz KR, Fulop SA: A unified theory of time-frequency reassignment. Comput. Res. Repository (CoRR) 2009., abs\/0903.3080:"},{"issue":"6","key":"81_CR19","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1109\/78.923298","volume":"49","author":"PJ Loughlin","year":"2001","unstructured":"Loughlin PJ, Davidson KL: Modified Cohen-Lee time-frequency distributions and instantaneous bandwidth of multicomponent signals. IEEE Trans. Signal Process 2001, 49(6):1153-1165. 10.1109\/78.923298","journal-title":"IEEE Trans. Signal Process"},{"key":"81_CR20","volume-title":"Speech Spectrum Analysis","year":"2011","unstructured":"Fulop SA , (Ed): Speech Spectrum Analysis. Heidelberg: Springer; 2011."},{"key":"81_CR21","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1109\/TASSP.1978.1163047","volume":"26","author":"K Kodera","year":"1978","unstructured":"Kodera K, Gendrin R, Villedary C: Analysis of time-varying signals with small BT values. IEEE Trans Acoustics, Speech Signal Process 1978, 26: 64-76. 10.1109\/TASSP.1978.1163047","journal-title":"IEEE Trans Acoustics, Speech Signal Process"},{"issue":"4","key":"81_CR22","doi-asserted-by":"publisher","first-page":"1292","DOI":"10.1109\/TSA.2005.858545","volume":"14","author":"T Abe","year":"2006","unstructured":"Abe T, Honda M: Sinusoidal model based on instantaneous frequency attractors. IEEE Trans. Audio, Speech Lang, Process 2006, 14(4):1292-1300.","journal-title":"IEEE Trans. Audio, Speech Lang, Process"},{"key":"81_CR23","first-page":"1429","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"DPW Ellis","year":"2007","unstructured":"Ellis DPW, Poliner GE: Identifying \u2018Cover Songs\u2019 with chroma features and dynamic programming beat tracking. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Honolulu; 2007:1429-1432."},{"key":"81_CR24","first-page":"14","volume-title":"Proceedings of the International Computer Music Conference (ICMC)","author":"SW Hainsworth","year":"2001","unstructured":"Hainsworth SW, Wolfe PJ: Time-frequency reassignment for music analysis. In Proceedings of the International Computer Music Conference (ICMC). Havana; 2001:14-17."},{"key":"81_CR25","first-page":"153","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"L Oudre","year":"2009","unstructured":"Oudre L, Grenier Y, F\u00e9votte C: Template-based chord recognition: influence of the chord types. In Proceedings of the International Conference on Music Information Retrieval (ISMIR). Kobe; 2009:153-158."},{"key":"81_CR26","volume-title":"Proceedings of the 118th Convention of the Audio Engineering Society (AES)","author":"C Harte","year":"2005","unstructured":"Harte C, Sandler M: Automatic chord identification using a quantized chromagram. In Proceedings of the 118th Convention of the Audio Engineering Society (AES). Spain; 2005."},{"key":"81_CR27","first-page":"121","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"H Papadopoulos","year":"2008","unstructured":"Papadopoulos H, Peeters G: Simultaneous estimation of chord progression and downbeats from an audio file. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Las Vegas; 2008:121-124."},{"key":"81_CR28","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/5.18626","volume":"77","author":"L Rabiner","year":"1989","unstructured":"Rabiner L: A tutorial on hidden Markov models and selected applications in speech recognition. Proc, IEEE 1989, 77: 257-286. 10.1109\/5.18626","journal-title":"Proc, IEEE"},{"key":"81_CR29","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/89.365379","volume":"3","author":"DA Reynolds","year":"1995","unstructured":"Reynolds DA, Rose RC: Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Trans. Speech Audio Process 1995, 3: 72-83. 10.1109\/89.365379","journal-title":"IEEE Trans. Speech Audio Process"},{"key":"81_CR30","first-page":"1","volume-title":"Proceedings of the Sound and Music Computing Conference (SMC)","author":"T Cho","year":"2010","unstructured":"Cho T, Weiss RJ, Bello JP: Exploring common variations in state of the art chord recognition systems. In Proceedings of the Sound and Music Computing Conference (SMC). Barcelona; 2010:1-8."},{"key":"81_CR31","first-page":"459","volume-title":"Time frequency reassignment: a review and analysis Technical report, Cambridge University Engineering Department, CUED\/F-INFENG\/TR","author":"SW Hainsworth","year":"2003","unstructured":"Hainsworth SW, Macleod MD: Time frequency reassignment: a review and analysis Technical report, Cambridge University Engineering Department, CUED\/F-INFENG\/TR. June 2003, 459."},{"issue":"43","key":"81_CR32","first-page":"1068","volume":"5","author":"F Auger","year":"1995","unstructured":"Auger F, Flandrin P: Improving the readability of time-frequency and time-scale representations by the reassignment method. IEEE Trans, Speech Audio Process 1995, 5(43):1068-1089.","journal-title":"IEEE Trans, Speech Audio Process"},{"issue":"3","key":"81_CR33","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1121\/1.2431329","volume":"121","author":"SA Fulop","year":"2007","unstructured":"Fulop SA, Fitz K: Separation of components from impulses in reassigned spectrograms. J. Acoust. Soc. Am 2007, 121(3):1510-1518. 10.1121\/1.2431329","journal-title":"J. Acoust. Soc. Am"},{"issue":"2\u20133","key":"81_CR34","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1006\/dspr.2002.0456","volume":"12","author":"DJ Nelson","year":"2002","unstructured":"Nelson DJ: Instantaneous higher order phase derivatives. Digit Signal Process 2002, 12(2\u20133):416-428.","journal-title":"Digit Signal Process"},{"key":"81_CR35","first-page":"506","volume-title":"Proceedings of the International Conference on Digital Audio Effects DAFx","author":"M Khadkevich","year":"2009","unstructured":"Khadkevich M, Omologo M: Phase-change based tuning for automatic chord recognition. In Proceedings of the International Conference on Digital Audio Effects DAFx. Como; 2009:506-509."},{"key":"81_CR36","volume-title":"PhD thesis, Universitat Pompeu Fabra","author":"E G\u00f3mez","year":"2006","unstructured":"G\u00f3mez E: Tonal description of music audio signals. PhD thesis, Universitat Pompeu Fabra 2006."},{"key":"81_CR37","volume-title":"PhD thesis, Center for Computer Research in Music and Acoustics (CCRMA)","author":"K Lee","year":"2008","unstructured":"Lee K: A system for acoustic chord transcription and key extraction from audio using hidden Markov models trained on synthesized audio. In PhD thesis, Center for Computer Research in Music and Acoustics (CCRMA). Department of Music, Stanford University; 2008."},{"key":"81_CR38","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/0167-6393(95)00009-D","volume":"17","author":"DA Reynolds","year":"1995","unstructured":"Reynolds DA: Speaker identification and verification using Gaussian mixture speaker models. Speech Commun 1995., 17(91\u2013108):","journal-title":"Speech Commun"},{"key":"81_CR39","first-page":"127","volume-title":"Proceedings of the International Conference on Digital Audio Effects DAFx","author":"G Peeters","year":"2006","unstructured":"Peeters G: Musical key estimation of audio signal based on HMM modeling of chroma vectors. In Proceedings of the International Conference on Digital Audio Effects DAFx. McGill; 2006:127-131."},{"key":"81_CR40","doi-asserted-by":"crossref","first-page":"115","DOI":"10.21437\/Interspeech.2008-26","volume-title":"Proceedings of Interspeech","author":"C Zieger","year":"2008","unstructured":"Zieger C, Omologo M: Acoustic event classification using a distributed microphone network with a GMM\/SVM combined algorithm. In Proceedings of Interspeech. Brisbane; 2008:115-118."},{"key":"81_CR41","unstructured":"Signal Processing Methods for Music Transcription. 2006."},{"key":"81_CR42","unstructured":"Speech and Language Processing: An Introduction to Natural Language Processing Computational Linguistics, and Speech Recognition. 2000."},{"key":"81_CR43","first-page":"66","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"C Harte","year":"2005","unstructured":"Harte C, Sandler M: Symbolic representation of musical chords: a proposed syntax for text annotations. In Proceedings of the International Conference on Music Information Retrieval (ISMIR). London; 2005:66-71."},{"issue":"6","key":"81_CR44","doi-asserted-by":"publisher","first-page":"1280","DOI":"10.1109\/TASL.2009.2032947","volume":"18","author":"M Mauch","year":"2010","unstructured":"Mauch M, Dixon S: Simultaneous estimation of chords and musical context from audio. IEEE Trans. Audio, Speech, Lang, Process 2010, 18(6):1280-1289.","journal-title":"IEEE Trans. Audio, Speech, Lang, Process"},{"key":"81_CR45","first-page":"409","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"C Joder","year":"2010","unstructured":"Joder C, Essid S, Richard G: A comparative study of tonal acoustic features for a symbolic level music-to-score alignment. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Dallas; 2010:409-412."},{"key":"81_CR46","first-page":"287","volume-title":"Proceedings of the International Conference on Music Information Retrieval (ISMIR)","author":"M Goto","year":"2002","unstructured":"Goto M, Hashiguchi H, Nishimura T, Oka R: RWC music database: popular, classical, and jazz music databases. In Proceedings of the International Conference on Music Information Retrieval (ISMIR). Paris; 2002:287-288."},{"key":"81_CR47","first-page":"445","volume-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"M Khadkevich","year":"2012","unstructured":"Khadkevich M, Fillon T, Richard G, Omologo M: A probabilistic approach to simultaneous extraction of beats and downbeats. In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Kyoto; 2012:445-448."}],"container-title":["EURASIP Journal on Audio, Speech, and Music Processing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1687-4722-2013-15\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2013-15.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1687-4722-2013-15.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,26]],"date-time":"2022-02-26T15:08:15Z","timestamp":1645888095000},"score":1,"resource":{"primary":{"URL":"https:\/\/asmp-eurasipjournals.springeropen.com\/articles\/10.1186\/1687-4722-2013-15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,6,27]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2013,12]]}},"alternative-id":["81"],"URL":"https:\/\/doi.org\/10.1186\/1687-4722-2013-15","relation":{},"ISSN":["1687-4722"],"issn-type":[{"value":"1687-4722","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,6,27]]},"article-number":"15"}}