{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T05:20:40Z","timestamp":1737436840165,"version":"3.33.0"},"reference-count":51,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"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":[[2024,12,2]]},"DOI":"10.1109\/slt61566.2024.10832291","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:27Z","timestamp":1737052287000},"page":"899-905","source":"Crossref","is-referenced-by-count":0,"title":["Massively Multilingual Forced Aligner Leveraging Self-Supervised Discrete Units"],"prefix":"10.1109","author":[{"given":"Hirofumi","family":"Inaguma","sequence":"first","affiliation":[{"name":"Meta,USA"}]},{"given":"Ilia","family":"Kulikov","sequence":"additional","affiliation":[{"name":"Meta,USA"}]},{"given":"Zhaoheng","family":"Ni","sequence":"additional","affiliation":[{"name":"Meta,USA"}]},{"given":"Sravya","family":"Popuri","sequence":"additional","affiliation":[{"name":"Meta,USA"}]},{"given":"Paden","family":"Tomasello","sequence":"additional","affiliation":[{"name":"Meta,USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"article-title":"FastSpeech 2: Fast and high-quality end-to-end text to speech","volume-title":"Proc. ICLR","author":"Ren","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3362\/0262-8104.2002.009"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.486"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.216"},{"key":"ref6","first-page":"1399","article-title":"A3t: Alignment-aware acoustic and text pre-training for speech synthesis and editing","volume-title":"Proc. ICML","author":"Bai"},{"key":"ref7","article-title":"SpiRit-LM: Interleaved spoken and written language model","author":"Nguyen","year":"2024","journal-title":"arXiv preprint arXiv:2402.05755"},{"article-title":"The Kaldi speech recognition toolkit","volume-title":"Proc. ASRU","author":"Povey","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1676"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10940"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746112"},{"key":"ref13","article-title":"Scaling speech technology to 1,000+ languages","author":"Pratap","year":"2023","journal-title":"arXiv preprint arXiv:2305.13516"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_27"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178778"},{"key":"ref16","article-title":"Connectionist temporal classification with maximum entropy regularization","volume-title":"Proc. NeurIPS","volume":"31","author":"Liu"},{"key":"ref17","article-title":"Why does CTC result in peaky behavior?","author":"Zeyer","year":"2021","journal-title":"arXiv preprint arXiv:2105.14849"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097248"},{"key":"ref19","article-title":"The importance of accurate alignments in end-to-end speech synthesis","author":"Prakash","year":"2022","journal-title":"arXiv preprint arXiv:2210.17153"},{"key":"ref20","article-title":"XLS-R: Self-supervised cross-lingual speech representation learning at scale","author":"Babu","year":"2021","journal-title":"arXiv preprint arXiv:2111.09296"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-475"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1059"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-894"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-78"},{"key":"ref25","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref26","article-title":"VALL-T: Decoder-only generative transducer for robust and decoding-controllable text-to-speech","author":"Du","year":"2024","journal-title":"arXiv preprint arXiv:2401.14321"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1211.3711"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446111"},{"key":"ref29","article-title":"ZMM-TTS: Zero-shot multilingual and multispeaker speech synthesis conditioned on self-supervised discrete speech representations","author":"Gong","year":"2023","journal-title":"arXiv preprint arXiv:2312.14398"},{"key":"ref30","article-title":"Seamless: Multilingual expressive and streaming speech translation","author":"Barrault","year":"2023","journal-title":"arXiv preprint arXiv:2312.05187"},{"key":"ref31","article-title":"SeamlessM4T-Massively Multilingual & Multimodal Machine Translation","author":"Barrault","year":"2023","journal-title":"arXiv preprint arXiv:2308.11596"},{"key":"ref32","article-title":"Exploring speech enhancement for low-resource speech synthesis","author":"Ni","year":"2023","journal-title":"arXiv preprint arXiv:2309.10795"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.155"},{"volume-title":"ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models","key":"ref36","article-title":"RAD-TTS: Parallel flow-based TTS with robust alignment learning and diverse synthesis"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref38","first-page":"8067","article-title":"Glow-TTS: A generative flow for text-to-speech via monotonic alignment search","volume-title":"Proc. NeurIPS","volume":"33","author":"Kim"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1905"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/SLT54892.2023.10023141"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-2409"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov","key":"ref43"},{"key":"ref44","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. NeurIPS","volume":"33","author":"Kong"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2004.09.001"},{"key":"ref46","article-title":"Timit acoustic phonetic continuous speech corpus","volume":"19","year":"1993","journal-title":"Linguistic Data Consortium"},{"key":"ref47","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. NeurIPS","volume":"33","author":"Baevski"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2013"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-439"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1508"}],"event":{"name":"2024 IEEE Spoken Language Technology Workshop (SLT)","start":{"date-parts":[[2024,12,2]]},"location":"Macao","end":{"date-parts":[[2024,12,5]]}},"container-title":["2024 IEEE Spoken Language Technology Workshop (SLT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830790\/10830793\/10832291.pdf?arnumber=10832291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:21Z","timestamp":1737398361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10832291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/slt61566.2024.10832291","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]}}}