{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T15:04:48Z","timestamp":1784646288242,"version":"3.55.0"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/taslp.2022.3169634","type":"journal-article","created":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T19:37:08Z","timestamp":1651001828000},"page":"1679-1693","source":"Crossref","is-referenced-by-count":9,"title":["Zero-Shot Normalization Driven Multi-Speaker Text to Speech Synthesis"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0485-392X","authenticated-orcid":false,"given":"Neeraj","family":"Kumar","sequence":"first","affiliation":[{"name":"Bharti School of Telecommunication Technology and Management, Indian Institute of Technology Delhi, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankur","family":"Narang","sequence":"additional","affiliation":[{"name":"Bharti School of Telecommunication Technology and Management, Indian Institute of Technology Delhi, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2677-3071","authenticated-orcid":false,"given":"Brejesh","family":"Lall","sequence":"additional","affiliation":[{"name":"Bharti School of Telecommunication Technology and Management, Indian Institute of Technology Delhi, New Delhi, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"CSTR VCTK corpus: English multi-speaker corpus for CSTR voice cloning toolkit (version 0.92)","author":"Yamagishi","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref3","article-title":"Artificial intelligence: A modern approach","author":"Russell","year":"2003","journal-title":"Prentice Hall Ser. Artif. Intell."},{"key":"ref4","volume-title":"Foundations of Statistical Natural Language Processing","author":"Manning","year":"1999"},{"key":"ref5","volume-title":"Speech & Language Processing","author":"Jurafsky","year":"2000"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2307\/538001"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-48830-9_2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21236\/ADA110902"},{"key":"ref9","volume-title":"Pattern Recognition and Machine Learning","author":"Bishop","year":"2006"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa8415"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref12","article-title":"Fastspeech: Fast, robust and controllable text to speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren","year":"2019"},{"key":"ref13","article-title":"Fastspeech 2: Fast and high-quality end-to-end text-to-speech","author":"Ren","year":"2021"},{"key":"ref14","article-title":"Voice synthesis for in-the-wild speakers via a phonological loop","author":"Taigman","year":"2017"},{"key":"ref15","first-page":"3683","article-title":"Fitting new speakers based on a short untranscribed sample","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nachmani","year":"2018"},{"key":"ref16","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jia","year":"2018"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3139"},{"key":"ref18","article-title":"Neural voice cloning with a few samples","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Arik","year":"2018"},{"key":"ref19","article-title":"Deep voice 2: Multi-speaker neural text-to-speech","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Arik","year":"2017"},{"key":"ref20","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","author":"Ping","year":"2017"},{"key":"ref21","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Skerry-Ryan","year":"2018"},{"key":"ref22","first-page":"5180","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683623"},{"key":"ref24","article-title":"Autoencoding variational inference for topic models","volume-title":"Proc. ICLR","author":"Srivastava","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"ref26","article-title":"End-to-end adversarial text-to-speech","author":"Donahue","year":"2021"},{"key":"ref27","article-title":"Adaspeech: Adaptive text to speech for custom voice","author":"Chen","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414872"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-329"},{"key":"ref31","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski","year":"2020"},{"key":"ref32","article-title":"Hierarchical generative modeling for controllable speech synthesis","author":"Hsu","year":"2019"},{"key":"ref33","article-title":"Close to human quality TTS with transformer","author":"Li","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054535"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/k16-1002"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1774"},{"key":"ref40","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","author":"Kim","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2867"},{"key":"ref42","first-page":"933","article-title":"Language modeling with gated convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dauphin","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1064"},{"key":"ref44","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"ref46","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref47","article-title":"Gaussian error linear units (gelus)","volume":"2016","author":"Hendrycks"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(98)00085-5"},{"key":"ref51","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in English and Mandarin","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Amodei","year":"2016"},{"key":"ref52","article-title":"G2pE","volume-title":"GitHub Repository","author":"Park","year":"2019"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2593263"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4960497"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1121\/1.1458024"},{"key":"ref57","first-page":"2232","article-title":"An investigation into neural net optimization via hessian eigenvalue density","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ghorbani","year":"2019"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1137\/16M1104974"},{"key":"ref59","article-title":"The full spectrum of deepnet Hessians at scale: Dynamics with SGD training and sample size","author":"Papyan","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1137\/130934283"},{"issue":"1","key":"ref61","first-page":"71","article-title":"Some large-scale matrix computation problems","volume-title":"J. Comput. Appl. Math.","volume":"74","author":"Bai","year":"1996"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/BF02142693"},{"key":"ref63","first-page":"29","article-title":"Bounds for the trace of the inverse and the determinant of symmetric positive de nite","volume-title":"Ann. Numer. Math.","volume":"4","author":"Bai","year":"1996"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1515\/9781400833887"},{"key":"ref65","first-page":"161","article-title":"The tradeoffs of large scale learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bottou","year":"2008"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref67","article-title":"The effect of network depth on the optimization landscape","author":"Ghorbani","year":"2019"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1214\/ECP.v18-2865"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3122-7"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_64474"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-97-00861-2"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1137\/130934283"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9657755\/09763046.pdf?arnumber=9763046","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T00:51:38Z","timestamp":1706057498000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9763046\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/taslp.2022.3169634","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}