{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:23:17Z","timestamp":1774419797496,"version":"3.50.1"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890256","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["TTS-Transducer: End-to-End Speech Synthesis with Neural Transducer"],"prefix":"10.1109","author":[{"given":"Vladimir","family":"Bataev","sequence":"first","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Subhankar","family":"Ghosh","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vitaly","family":"Lavrukhin","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Li","sequence":"additional","affiliation":[{"name":"NVIDIA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"FastSpeech: Fast, robust and controllable text to speech","volume-title":"NeurIPS","author":"Ren"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1770"},{"key":"ref3","article-title":"Sequence to sequence learning with neural networks","volume-title":"NIPS","author":"Sutskever"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP.2018.8461368","article-title":"Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions","volume-title":"ICASSP","author":"Shen"},{"key":"ref5","article-title":"Deep Voice 3: Scaling text-to-speech with convolutional sequence learning","volume-title":"ICLR","author":"Ping"},{"key":"ref6","article-title":"Sequence transduction with Recurrent Neural Networks","volume-title":"ICML Workshop on Representation Learning","author":"Graves"},{"key":"ref7","article-title":"High fidelity neural audio compression","author":"D\u2019efossez","year":"2022"},{"key":"ref8","article-title":"High-fidelity audio compression with improved RVQGAN","volume-title":"NeurIPS","author":"Kumar"},{"key":"ref9","article-title":"Spectral codecs: Spectrogram-based audio codecs for high quality speech synthesis","author":"Langman","year":"2024"},{"key":"ref10","article-title":"Neural codec language models are zero-shot text to speech synthesizers","author":"Wang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-335"},{"key":"ref12","article-title":"Bark: Text-prompted generative audio model","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419418"},{"key":"ref14","article-title":"Style tokens: Unsupervised style modeling, control and transfer in end-to-end speech synthesis","volume-title":"ICML","author":"Wang"},{"key":"ref15","article-title":"Attention is all you need","volume-title":"NeurIPS","author":"Vaswani"},{"key":"ref16","article-title":"Nemo: a toolkit for building AI applications using neural modules","volume-title":"NeurIPS Workshop on Systems for ML","author":"Kuchaiev"},{"key":"ref17","article-title":"The curious case of neural text degeneration","volume-title":"ICLR","author":"Holtzman"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2019-38"},{"key":"ref19","article-title":"Speech-T: Transducer for text to speech and beyond","volume-title":"NeurIPS","author":"Chen"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389791"},{"key":"ref21","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"NeurIPS","author":"Baevski"},{"key":"ref22","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","volume-title":"ICML","author":"Kim"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-465"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10890943"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref26","article-title":"UniAudio: An audio foundation model toward universal audio generation","author":"Yang","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.393"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref30","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref31","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"NeurIPS","author":"Jia"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2313"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096679"},{"key":"ref34","article-title":"Speech recognition with next-generation Kaldi (K2, Lhotse, Icefall)","volume-title":"Interspeech","author":"Povey"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SLT61566.2024.10832333"},{"key":"ref36","article-title":"Speak foreign languages with your own voice: Cross-lingual neural codec language modeling","author":"Zhang","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1584"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"ref39","article-title":"CSTR VCTK Corpus: English Multi-speaker Corpus for CSTR Voice Cloning Toolkit (version 0.92)","volume-title":"University of Edinburgh","author":"Yamagishi","year":"2019"},{"key":"ref40","article-title":"Decoupled weight decay regularization","volume-title":"ICLR","author":"Loshchilov"},{"key":"ref41","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"ICLR","author":"Loshchilov"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890256.pdf?arnumber=10890256","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:45Z","timestamp":1774416285000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890256\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890256","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}