{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T15:09:11Z","timestamp":1788707351734,"version":"build-2803163510"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,7,30]],"date-time":"2027-07-30T00:00:00Z","timestamp":1816905600000},"content-version":"am","delay-in-days":179,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100017186","name":"Ohio Supercomputer Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017186","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000055","name":"National Institute on Deafness and Other Communication Disorders","doi-asserted-by":"publisher","award":["R01DC012048"],"award-info":[{"award-number":["R01DC012048"]}],"id":[{"id":"10.13039\/100000055","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Speech & Language"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.csl.2026.102028","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T14:57:14Z","timestamp":1784645834000},"page":"102028","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Talker-independent multi-pitch tracking in noisy and reverberant scenarios"],"prefix":"10.1016","volume":"102","author":[{"given":"Yixuan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heming","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"DeLiang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2026.102028_b1","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1121\/1.382599","article-title":"Image method for efficiently simulating small-room acoustics","volume":"65","author":"Allen","year":"1979","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.csl.2026.102028_b2","doi-asserted-by":"crossref","unstructured":"Ardaillon, L., Roebel, A., 2019. Fully-convolutional network for pitch estimation of speech signals. In: Proc. Interspeech.","DOI":"10.21437\/Interspeech.2019-2815"},{"key":"10.1016\/j.csl.2026.102028_b3","doi-asserted-by":"crossref","unstructured":"Bach, F.R., Jordan, M.I., 2005. Discriminative training of hidden Markov models for multiple pitch tracking. In: Proc. ICASSP. Vol. 5, pp. 489\u2013492.","DOI":"10.1109\/ICASSP.2005.1416347"},{"key":"10.1016\/j.csl.2026.102028_b4","doi-asserted-by":"crossref","unstructured":"Bagshaw, P.C., Hiller, S.M., Jack, M.A., 1993. Enhanced pitch tracking and the processing of F0 contours for computer aided intonation teaching. In: Proc. Eurospeech. pp. 1003\u20131006.","DOI":"10.21437\/Eurospeech.1993-241"},{"key":"10.1016\/j.csl.2026.102028_b5","first-page":"341","article-title":"PRAAT, a system for doing phonetics by computer","volume":"5","author":"Boersma","year":"2001","journal-title":"Glot Int."},{"key":"10.1016\/j.csl.2026.102028_b6","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1109\/TASL.2008.2009578","article-title":"Analysis of emotionally salient aspects of fundamental frequency for emotion detection","volume":"17","author":"Busso","year":"2009","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2026.102028_b7","doi-asserted-by":"crossref","first-page":"1638","DOI":"10.1121\/1.2951592","article-title":"SWIPE: A sawtooth waveform inspired pitch estimator for speech and music","volume":"124","author":"Camacho","year":"2008","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.csl.2026.102028_b8","doi-asserted-by":"crossref","first-page":"2604","DOI":"10.1121\/1.4948445","article-title":"Large-scale training to increase speech intelligibility for hearing-impaired listeners in novel noises","volume":"139","author":"Chen","year":"2016","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.csl.2026.102028_b9","series-title":"Multi-Pitch Estimation","author":"Christensen","year":"2009"},{"key":"10.1016\/j.csl.2026.102028_b10","unstructured":"Dauphin, Y.N., Fan, A., Auli, M., Grangier, D., 2017. Language modeling with gated convolutional networks. In: Proc. ICML. pp. 933\u2013941."},{"key":"10.1016\/j.csl.2026.102028_b11","doi-asserted-by":"crossref","first-page":"1917","DOI":"10.1121\/1.1458024","article-title":"YIN, a fundamental frequency estimator for speech and music","volume":"111","author":"De Cheveign\u00e9","year":"2002","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.csl.2026.102028_b12","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1109\/TASLP.2013.2285484","article-title":"Multi-pitch streaming of harmonic sound mixtures","volume":"22","author":"Duan","year":"2013","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2026.102028_b13","unstructured":"Flego, F., Omologo, M., 2006. Robust F0 estimation based on a multichannel periodicity function for distant-talking speech. In: Proc. EU-USIP."},{"key":"10.1016\/j.csl.2026.102028_b14","doi-asserted-by":"crossref","unstructured":"Gao, F., Wu, L., Zhao, L., Qin, T., Cheng, X., Liu, T.-Y., 2018. Efficient sequence learning with group recurrent networks. In: Proc. NAACL-HLT. pp. 799\u2013808.","DOI":"10.18653\/v1\/N18-1073"},{"key":"10.1016\/j.csl.2026.102028_b15","series-title":"DARPA TIMIT acoustic phonetic continuous speech corpus","author":"Garofolo","year":"1993"},{"key":"10.1016\/j.csl.2026.102028_b16","doi-asserted-by":"crossref","first-page":"2158","DOI":"10.1109\/TASLP.2014.2363410","article-title":"Neural network based pitch tracking in very noisy speech","volume":"22","author":"Han","year":"2014","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2026.102028_b17","doi-asserted-by":"crossref","unstructured":"Hershey, J.R., Chen, Z., Le Roux, J., Watanabe, S., 2016. Deep clustering: Discriminative embeddings for segmentation and separation. In: Proc. ICASSP. pp. 31\u201335.","DOI":"10.1109\/ICASSP.2016.7471631"},{"key":"10.1016\/j.csl.2026.102028_b18","doi-asserted-by":"crossref","first-page":"1091","DOI":"10.1109\/TASL.2010.2077280","article-title":"HMM-based multipitch tracking for noisy and reverberant speech","volume":"19","author":"Jin","year":"2010","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2026.102028_b19","doi-asserted-by":"crossref","first-page":"4999","DOI":"10.1109\/TASLP.2024.3492803","article-title":"TF-CrossNet: Leveraging global, cross-band, narrow-band, and positional encoding for single- and multi-channel speaker separation","volume":"32","author":"Kalkhorani","year":"2024","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2026.102028_b20","doi-asserted-by":"crossref","unstructured":"Kawahara, H., Morise, M., Takahashi, T., Nisimura, R., Irino, T., Banno, H., 2008. Tandem-STRAIGHT: A temporally stable power spectral representation for periodic signals and applications to interference-free spectrum, F0, and aperiodicity estimation. In: Proc. ICASSP. pp. 3933\u20133936.","DOI":"10.1109\/ICASSP.2008.4518514"},{"key":"10.1016\/j.csl.2026.102028_b21","doi-asserted-by":"crossref","unstructured":"Kim, J.W., Salamon, J., Li, P., Bello, J.P., 2018. CREPE: A convolutional representation for pitch estimation. In: Proc. ICASSP. pp. 161\u2013165.","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"10.1016\/j.csl.2026.102028_b22","unstructured":"Kingma, D.P., Ba, J., 2014. Adam: A method for stochastic optimization. In: Proc. ICLR."},{"key":"10.1016\/j.csl.2026.102028_b23","doi-asserted-by":"crossref","first-page":"1901","DOI":"10.1109\/TASLP.2017.2726762","article-title":"Multitalker speech separation with utterance-level permutation invariant training of deep recurrent neural networks","volume":"25","author":"Kolb\u00e6k","year":"2017","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2026.102028_b24","unstructured":"Kominek, J., Black, A.W., 2004. The CMU Arctic speech databases. In: Proc. ISCA Workshop on Speech Synthesis. pp. 223\u2013224."},{"key":"10.1016\/j.csl.2026.102028_b25","unstructured":"Laube, S., Panos, B., 2025. COREPIT: A Convolutional Real-Time Pitch Tracker. In: Proc. ISMIR."},{"key":"10.1016\/j.csl.2026.102028_b26","doi-asserted-by":"crossref","unstructured":"Li, X., Liu, R., Song, T., Wu, X., Chen, J., 2020. Single-Channel Speech Separation Integrating Pitch Information Based on a Multi Task Learning Framework. In: Proc. ICASSP. pp. 7279\u20137283.","DOI":"10.1109\/ICASSP40776.2020.9053460"},{"key":"10.1016\/j.csl.2026.102028_b27","doi-asserted-by":"crossref","unstructured":"Li, X., Sun, Y., Wu, X., Chen, J., 2022. Multi-speaker pitch tracking via embodied self-supervised learning. In: Proc. ICASSP. pp. 8257\u20138261.","DOI":"10.1109\/ICASSP43922.2022.9747262"},{"key":"10.1016\/j.csl.2026.102028_b28","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, D.L., 2018. Permutation invariant training for speaker-independent multi-pitch tracking. In: Proc. ICASSP. pp. 5594\u20135598.","DOI":"10.1109\/ICASSP.2018.8461526"},{"key":"10.1016\/j.csl.2026.102028_b29","doi-asserted-by":"crossref","first-page":"2092","DOI":"10.1109\/TASLP.2019.2941148","article-title":"Divide and conquer: A deep CASA approach to talker-independent monaural speaker separation","volume":"27","author":"Liu","year":"2019","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2026.102028_b30","doi-asserted-by":"crossref","unstructured":"Luo, Y., Chen, Z., Yoshioka, T., 2020. Dual-path RNN: Efficient long sequence modeling for time-domain single-channel speech separation. In: Proc. ICASSP. pp. 46\u201350.","DOI":"10.1109\/ICASSP40776.2020.9054266"},{"key":"10.1016\/j.csl.2026.102028_b31","doi-asserted-by":"crossref","first-page":"1256","DOI":"10.1109\/TASLP.2019.2915167","article-title":"Conv-TasNet: Surpassing ideal time\u2013frequency magnitude masking for speech separation","volume":"27","author":"Luo","year":"2019","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2026.102028_b32","doi-asserted-by":"crossref","first-page":"570","DOI":"10.1109\/TASSP.1975.1162750","article-title":"A semiautomatic pitch detector (SAPD)","volume":"23","author":"McGonegal","year":"1975","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"10.1016\/j.csl.2026.102028_b33","unstructured":"Morise, M., Kawahara, H., Katayose, H., 2009. Fast and reliable F0 estimation method based on the period extraction of vocal fold vibration of singing voice and speech. In: Proc. AES 35th International Conference."},{"key":"10.1016\/j.csl.2026.102028_b34","doi-asserted-by":"crossref","first-page":"1877","DOI":"10.1587\/transinf.2015EDP7457","article-title":"WORLD: A vocoder-based high-quality speech synthesis system for real-time applications","volume":"99","author":"Morise","year":"2016","journal-title":"IEICE Trans. Inf. Syst."},{"key":"10.1016\/j.csl.2026.102028_b35","series-title":"Cross-domain neural pitch and periodicity estimation","author":"Morrison","year":"2023"},{"key":"10.1016\/j.csl.2026.102028_b36","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S., 2015. LibriSpeech: An ASR corpus based on public domain audio books. In: Proc. ICASSP. pp. 5206\u20135210.","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"10.1016\/j.csl.2026.102028_b37","doi-asserted-by":"crossref","unstructured":"Pirker, G., Wohlmayr, M., Petrik, S., Pernkopf, F., 2011. A pitch tracking corpus with evaluation on multipitch tracking scenario. In: Proc. Interspeech.","DOI":"10.21437\/Interspeech.2011-317"},{"key":"10.1016\/j.csl.2026.102028_b38","unstructured":"Plante, F., Meyer, G., Ainsworth, W., 1995. A pitch extraction reference database. In: Proc. Eurospeech. Vol. 8, pp. 30\u201350."},{"key":"10.1016\/j.csl.2026.102028_b39","doi-asserted-by":"crossref","unstructured":"Prasanna, S.R.M., Yegnanarayana, B., 2004. Extraction of pitch in adverse conditions. In: Proc. ICASSP. Vol. 1, pp. 109\u2013112.","DOI":"10.1109\/ICASSP.2004.1325934"},{"key":"10.1016\/j.csl.2026.102028_b40","doi-asserted-by":"crossref","unstructured":"Stasiak, B., Rychlicki-Kicior, K., 2012. Fundamental frequency extraction in speech emotion recognition. In: Proc. MCSS. pp. 292\u2013303.","DOI":"10.1007\/978-3-642-30721-8_29"},{"key":"10.1016\/j.csl.2026.102028_b41","doi-asserted-by":"crossref","unstructured":"Taherian, H., Kalkhorani, V.A., Pandey, A., Wong, D., Xu, B., Wang, D.L., 2024. Towards Explainable Monaural Speaker Separation with Auditory-based Training. In: Proc. Interspeech. pp. 572\u2013576.","DOI":"10.21437\/Interspeech.2024-530"},{"key":"10.1016\/j.csl.2026.102028_b42","doi-asserted-by":"crossref","unstructured":"Takagi, M., Nishihara, M., Hono, Y., Hashimoto, K., Nankaku, Y., Tokuda, K., 2025. PeriodCodec: A Pitch-Controllable Neural Audio Codec Using Periodic Signals for Singing Voice Synthesis. In: Proc. Interspeech. pp. 4913\u20134917.","DOI":"10.21437\/Interspeech.2025-347"},{"key":"10.1016\/j.csl.2026.102028_b43","first-page":"518","article-title":"A robust algorithm for pitch tracking (RAPT)","volume":"495","author":"Talkin","year":"1995","journal-title":"Speech Coding Synth."},{"key":"10.1016\/j.csl.2026.102028_b44","doi-asserted-by":"crossref","unstructured":"Tzinis, E., Wang, Z., Smaragdis, P., 2020. Sudo rm-rf: Efficient networks for universal audio source separation. In: Proc. MLSP. pp. 1\u20136.","DOI":"10.1109\/MLSP49062.2020.9231900"},{"key":"10.1016\/j.csl.2026.102028_b45","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1250\/ast.25.232","article-title":"An improved method based on the MTF concept for restoring the power envelope from a reverberant signal","volume":"25","author":"Unoki","year":"2004","journal-title":"Acoust. Sci. Technol."},{"key":"10.1016\/j.csl.2026.102028_b46","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/0167-6393(93)90095-3","article-title":"Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems","volume":"12","author":"Varga","year":"1993","journal-title":"Speech Commun."},{"key":"10.1016\/j.csl.2026.102028_b47","doi-asserted-by":"crossref","first-page":"3221","DOI":"10.1109\/TASLP.2023.3304482","article-title":"TF-GridNet: Integrating full-and sub-band modeling for speech separation","volume":"31","author":"Wang","year":"2023","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2026.102028_b48","doi-asserted-by":"crossref","first-page":"799","DOI":"10.1109\/TASL.2010.2064309","article-title":"A probabilistic interaction model for multipitch tracking with factorial hidden Markov models","volume":"19","author":"Wohlmayr","year":"2010","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2026.102028_b49","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1109\/TSA.2003.811539","article-title":"A multipitch tracking algorithm for noisy speech","volume":"11","author":"Wu","year":"2003","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/j.csl.2026.102028_b50","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, H., Wang, D.L., 2022. Densely-connected Convolutional Recurrent Network for Fundamental Frequency Estimation in Noisy Speech. In: Proc. Interspeech. pp. 401\u2013405.","DOI":"10.21437\/Interspeech.2022-11156"},{"key":"10.1016\/j.csl.2026.102028_b51","doi-asserted-by":"crossref","first-page":"3760","DOI":"10.1109\/TASLP.2023.3313427","article-title":"F0 estimation and voicing detection with cascade architecture in noisy speech","volume":"31","author":"Zhang","year":"2023","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"10.1016\/j.csl.2026.102028_b52","doi-asserted-by":"crossref","first-page":"3502","DOI":"10.1121\/10.0034445","article-title":"Leveraging laryngograph data for robust voicing detection in speech","volume":"156","author":"Zhang","year":"2024","journal-title":"J. Acoust. Soc. Am."}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230826000914?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230826000914?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T14:15:13Z","timestamp":1788704113000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230826000914"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":52,"alternative-id":["S0885230826000914"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2026.102028","relation":{},"ISSN":["0885-2308"],"issn-type":[{"value":"0885-2308","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Talker-independent multi-pitch tracking in noisy and reverberant scenarios","name":"articletitle","label":"Article Title"},{"value":"Computer Speech & Language","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csl.2026.102028","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"102028"}}