{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T07:23:11Z","timestamp":1782372191503,"version":"3.54.5"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,11,28]],"date-time":"2015-11-28T00:00:00Z","timestamp":1448668800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Speech Technol"],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1007\/s10772-015-9325-1","type":"journal-article","created":{"date-parts":[[2015,11,28]],"date-time":"2015-11-28T05:48:39Z","timestamp":1448689719000},"page":"65-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Pitch estimation of speech and music sound based on multi-scale product with auditory feature extraction"],"prefix":"10.1007","volume":"19","author":[{"given":"Mohamed Anouar","family":"Ben Messaoud","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A\u00efcha","family":"Bouzid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,11,28]]},"reference":[{"key":"9325_CR1","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1109\/TSA.2005.851998","volume":"13","author":"JP Bello","year":"2005","unstructured":"Bello, J. P., Daudet, L., Abdallah, S., & Duxbury, C. (2005). A tutorial on onset detection in music signals. IEEE Transactions on Speech, Audio Processing, 13, 1035\u20131048.","journal-title":"IEEE Transactions on Speech, Audio Processing"},{"key":"9325_CR2","first-page":"114","volume":"9","author":"MA Ben Messaoud","year":"2015","unstructured":"Ben Messaoud, M. A., Bouzid, A., & Ellouze, N. (2015). Automatic segmentation of the clean speech signal. World Academy of Science, Engineering and Technology International Journal of Electrical, Computer, Electronics and Communication Engineering, 9, 114\u2013117.","journal-title":"World Academy of Science, Engineering and Technology International Journal of Electrical, Computer, Electronics and Communication Engineering"},{"key":"9325_CR3","doi-asserted-by":"crossref","first-page":"2346","DOI":"10.1121\/1.400923","volume":"89","author":"J Brown","year":"1991","unstructured":"Brown, J., & Zhang, B. (1991). Musical frequency tracking using the methods of conventional and \u2019narrowed\u2019 autocorrelation. Journal of the Acoustic Society of America, 89, 2346\u20132354.","journal-title":"Journal of the Acoustic Society of America"},{"key":"9325_CR5","doi-asserted-by":"crossref","first-page":"1638","DOI":"10.1121\/1.2951592","volume":"124","author":"A Camacho","year":"2008","unstructured":"Camacho, A., & Harris, J. (2008). A sawtooth waveform inspired pitch estimator for speech and music. Journal of the Acoustic Society of America, 124, 1638\u20131652.","journal-title":"Journal of the Acoustic Society of America"},{"key":"9325_CR6","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. Journal of the Acoustic Society of America, 111, 1917\u20131930.","journal-title":"Journal of the Acoustic Society of America"},{"key":"9325_CR7","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1023\/A:1020201125377","volume":"5","author":"I Gavat","year":"2002","unstructured":"Gavat, I., Zira, M., & Sabac, B. (2002). Pitch estimation by block and instantaneous methods. International Journal of Speech Technology, 5, 269\u2013279.","journal-title":"International Journal of Speech Technology"},{"key":"9325_CR8","volume-title":"Advances in speech signal processing","author":"WJ Hess","year":"1992","unstructured":"Hess, W. J. (1992). Pitch and voicing determination. In S. Furni, M. Sondhi, & M. Dekker (Eds.), Advances in speech signal processing. New York: Marcel Dekker, Inc.,"},{"key":"9325_CR9","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1109\/TASL.2006.874669","volume":"14","author":"T Irino","year":"2006","unstructured":"Irino, T., & Patterson, R. D. (2006). A dynamic compressive gammachirp auditory filterbank. IEEE Transactions on Audio, Speech and Language Processing, 14, 2222\u20132253.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9325_CR10","doi-asserted-by":"crossref","unstructured":"Kawahara, H., Katayose, H., De Cheveign\u00e9, A., & Patterson, R. D. (1999). Fixed point analysis of frequency to instantaneous frequency mapping for accurate estimation of F0 and periodicity. Proceedings 6th EUROSPEECH (pp. 2781\u20132784).","DOI":"10.21437\/Eurospeech.1999-613"},{"key":"9325_CR11","unstructured":"Klapuri, A. (2000). Qualitative and quantitative aspects in the design of periodicity estimation algorithms. European signal processing conference proceedings (pp. 2069\u20132072)."},{"key":"9325_CR12","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1080\/0929821042000317840","volume":"33","author":"A Klapuri","year":"2004","unstructured":"Klapuri, A. (2004). Automatic music transcription as we know it today. Journal of New Music Research, 33, 269\u2013282.","journal-title":"Journal of New Music Research"},{"key":"9325_CR13","doi-asserted-by":"crossref","unstructured":"Kunieda, N., Shimamura, T., & Suzuki, J. (1996). Robust method of measurement of fundamental frequency by aclos: autocorrelation of log spectrum. International conference on acoustics, speech, and signal processing proceedings (pp. 232\u2013235). Atlanta, GA.","DOI":"10.1109\/ICASSP.1996.540333"},{"key":"9325_CR14","doi-asserted-by":"crossref","unstructured":"Li, H., Dai, B., & Lu, W. (2006). A pitch detection algorithm based on AMDF and ACF. International conference on acoustics, speech and signal processing proceedings. Toulouse (pp. 377\u2013380).","DOI":"10.1109\/ICASSP.2006.1660036"},{"key":"9325_CR15","doi-asserted-by":"crossref","unstructured":"Lyon, R. F., Katsiamis, A. G., & Drakakis, E. M. (2010). History and future of auditory filter models. Proceedings of 2010 IEEE international symposium on circuits and systems (ISCAS) (pp. 3809\u20133820).","DOI":"10.1109\/ISCAS.2010.5537724"},{"key":"9325_CR16","unstructured":"Mahmoodzadeh, A., Abutalebi, H. R., Soltanian-Zadeh, H., Sheikhzadeh, H. (2012). Single channel speech separation with a frame-based pitch range estimation method in modulation frequency. International symposium on telecommunications (pp. 609\u2013613)."},{"key":"9325_CR17","volume-title":"A wavelet tour of signal processing","author":"S Mallat","year":"1999","unstructured":"Mallat, S. (1999). A wavelet tour of signal processing. San Diego: Academic Press."},{"key":"9325_CR18","series-title":"Springer Handbook of Auditory Research","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4419-5934-8","volume-title":"Computational models of the auditory system","author":"R Meddis","year":"2010","unstructured":"Meddis, R., Lopez-Poveda, E. A., Fay, R. R., & Popper, A. N. (2010). Computational models of the auditory system., Springer Handbook of Auditory Research New York: Springer."},{"key":"9325_CR19","doi-asserted-by":"crossref","first-page":"1811","DOI":"10.1121\/1.420088","volume":"102","author":"R Meddis","year":"1997","unstructured":"Meddis, R., & O\u2019Mard, L. (1997). A unitary model for pitch perception. Journal of the Acoustic Society of America, 102, 1811\u20131820.","journal-title":"Journal of the Acoustic Society of America"},{"key":"9325_CR20","unstructured":"Meyer, G., Plante, F., & Ainsworth, W. A. (1995). A pitch extraction reference database. 4th European Conference on Speech Communication and Technology. EUROSPEECH\u201995, Madrid, pp. 837\u2013840."},{"key":"9325_CR21","doi-asserted-by":"crossref","first-page":"1088","DOI":"10.1109\/JSTSP.2011.2112333","volume":"5","author":"M Muller","year":"2011","unstructured":"Muller, M., Ellis, D., Klapuri, A., & Richard, G. (2011). Signal processing for music analysis. IEEE Journal of Selected Topics in Signal Processing, 5, 1088\u20131110.","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"key":"9325_CR22","doi-asserted-by":"crossref","first-page":"1529","DOI":"10.1121\/1.1600720","volume":"114","author":"RD Patterson","year":"2003","unstructured":"Patterson, R. D., Unoki, M., & Irino, T. (2003). Extending the domain of centre frequencies for the compressive gammachirp auditory filter. Journal of the Acoustic Society of America, 114, 1529\u20131570.","journal-title":"Journal of the Acoustic Society of America"},{"key":"9325_CR23","doi-asserted-by":"crossref","unstructured":"Prasanna, S. R. M., & Yegnanarayana, B. (2004). Extraction of pitch in adverse conditions. International conference on acoustics, speech and signal processing proceedings (pp. 109\u2013112).","DOI":"10.1109\/ICASSP.2004.1325934"},{"key":"9325_CR24","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1007\/s10772-011-9112-6","volume":"14","author":"SJ Roy","year":"2011","unstructured":"Roy, S. J., Molla, M. K. I., Hirose, K., & Hasan, M. K. (2011). Harmonic modification and data adaptive filtering based approach to robust pitch estimation. International Journal of Speech Technology, 14, 339\u2013349.","journal-title":"International Journal of Speech Technology"},{"key":"9325_CR25","doi-asserted-by":"crossref","unstructured":"Shahnaz, C., Zhu, W. P., & Ahmad, M. O. (2007). A robust pitch estimation algorithm in noise. International conference on acoustics, speech and signal processing proceedings (pp. 1037\u20131076).","DOI":"10.1109\/ICASSP.2007.367259"},{"key":"9325_CR4","doi-asserted-by":"crossref","unstructured":"Shahnaz, C. Zhu, W. P., & Ahmad, M. O. (2008). A pitch extraction algorithm in noise based on temporal and spectral representations. International conference on acoustics, speech and signal processing proceedings (pp. 4477\u20134480).","DOI":"10.1109\/ICASSP.2008.4518650"},{"key":"9325_CR26","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1109\/89.952490","volume":"9","author":"T Shimamura","year":"2001","unstructured":"Shimamura, T., & Kobayashi, H. (2001). Weighted autocorrelation for pitch extraction of noisy speech. IEEE Transactions on Speech and Audio Processing, 9, 727\u2013730.","journal-title":"IEEE Transactions on Speech and Audio Processing"},{"key":"9325_CR27","doi-asserted-by":"crossref","unstructured":"Sun, X. (2000). A pitch determination algorithm based on subharmonic-to-harmonic ratio. International conference on spoken language processing proceedings (pp. 676\u2013679). Beijing.","DOI":"10.21437\/ICSLP.2000-902"},{"key":"9325_CR28","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1109\/89.876309","volume":"8","author":"M Tolonen","year":"2000","unstructured":"Tolonen, M., & Karjalainen, M. (2000). A computationally efficient multipitch analysis model. IEEE Transactions on Speech and Audio Process, 8, 708\u2013716.","journal-title":"IEEE Transactions on Speech and Audio Process"},{"key":"9325_CR29","unstructured":"University of lowa. (2012). Electronic music studios. http:\/\/theremin.music.uiowa.edu ."},{"key":"9325_CR30","doi-asserted-by":"crossref","first-page":"3511","DOI":"10.1121\/1.402840","volume":"91","author":"LM Immerseel Van","year":"1992","unstructured":"Van Immerseel, L. M., & Martens, J. P. (1992). Pitch and voiced\/unvoiced determination with an auditory model. Journal of the Acoustic Society of America, 91, 3511\u20133526.","journal-title":"Journal of the Acoustic Society of America"},{"key":"9325_CR31","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","volume":"12","author":"A Varga","year":"1993","unstructured":"Varga, A. (1993). Assessment for automatic speech recognition: II. Noisex-92: A database and an experiment to study the effect of additive noise on speech recognition systems. Elsevier Speech Communication, 12, 247\u2013251.","journal-title":"Elsevier Speech Communication"},{"key":"9325_CR32","doi-asserted-by":"crossref","DOI":"10.1109\/9780470043387","volume-title":"Principles, computational auditory scene analysis: Algorithms, and applications","author":"DL Wang","year":"2006","unstructured":"Wang, D. L., & Brown, G. J. (2006). Principles, computational auditory scene analysis: Algorithms, and applications. Hoboken, NJ: Wiley\/IEEE Press."},{"key":"9325_CR33","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1109\/83.336245","volume":"3","author":"Y Xu","year":"1994","unstructured":"Xu, Y., Weaver, J., Healy, D., & Lu, J. (1994). Wavelet transform domain filters: A spatially selective noise filtration technique. IEEE Transactions on Image Processing, 3, 747\u2013758.","journal-title":"IEEE Transactions on Image Processing"}],"container-title":["International Journal of Speech Technology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-015-9325-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10772-015-9325-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10772-015-9325-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T00:27:25Z","timestamp":1692145645000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10772-015-9325-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,11,28]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,3]]}},"alternative-id":["9325"],"URL":"https:\/\/doi.org\/10.1007\/s10772-015-9325-1","relation":{},"ISSN":["1381-2416","1572-8110"],"issn-type":[{"value":"1381-2416","type":"print"},{"value":"1572-8110","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,11,28]]}}}