{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:25:00Z","timestamp":1775229900233,"version":"3.50.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746112","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8167-8171","source":"Crossref","is-referenced-by-count":32,"title":["Phone-to-Audio Alignment without Text: A Semi-Supervised Approach"],"prefix":"10.1109","author":[{"given":"Jian","family":"Zhu","sequence":"first","affiliation":[{"name":"University of Michigan,Department of Linguistics,Ann Arbor,USA"}]},{"given":"Cong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Radboud University,Center for Language Studies,Nijmegen,Netherlands"}]},{"given":"David","family":"Jurgens","sequence":"additional","affiliation":[{"name":"University of Michigan,School of Information,Ann Arbor,USA"}]}],"member":"263","reference":[{"key":"ref32","article-title":"g2pE","author":"park","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-demo.21"},{"key":"ref30","article-title":"DARPA TIMIT acoustic-phonetic continous speech corpus CD-ROM. NIST speech disc 1-1.1","author":"garofolo","year":"1993","journal-title":"NASA STI\/Recon Technical Report"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60276-5_27"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1115"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053182"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1676"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2398"},{"key":"ref15","article-title":"Towards unsupervised phone and word segmentation using self-supervised vector-quantized neural networks","author":"kamper","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1874"},{"key":"ref17","article-title":"Rad-tts: Parallel flow-based tts with robust alignment learning and diverse synthesis","author":"shih","year":"2021","journal-title":"ICML Workshop on Invertible Neural Networks Normalizing Flows and Explicit Likelihood Models"},{"key":"ref18","article-title":"One tts alignment to rule them all","author":"badlani","year":"2021"},{"key":"ref19","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2396"},{"key":"ref4","article-title":"Signal processing via web services: the use case webmaus","author":"kisler","year":"2012","journal-title":"Digital Humanities 2012 Conference"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref3","article-title":"FAVE (forced alignment and vowel extraction) program suite","author":"rosenfelder","year":"2011"},{"key":"ref6","article-title":"The kaldi speech recognition toolkit","author":"povey","year":"2011","journal-title":"ASRU"},{"key":"ref29","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2020","journal-title":"LREC"},{"key":"ref5","article-title":"Gentle","author":"ochshorn","year":"2017"},{"key":"ref8","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"NeurIPS"},{"key":"ref7","first-page":"12","article-title":"The HTK book","volume":"3","author":"young","year":"2002","journal-title":"Cambridge University Engineering Department"},{"key":"ref2","article-title":"Prosodylab-aligner: A tool for forced alignment of laboratory speech","author":"gorman","year":"2011","journal-title":"Canadian Acoustics"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"498","DOI":"10.21437\/Interspeech.2017-1386","article-title":"Montreal forced aligner: Trainable text-speech alignment using kaldi","volume":"2017","author":"mcauliffe","year":"2017","journal-title":"InterSpeech"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1073"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref24","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"ren","year":"2020","journal-title":"ICLRE"},{"key":"ref23","article-title":"Efficiently trainable text-to-speech sys-tem based on deep convolutional networks with guided attention","author":"tachibana","year":"2018","journal-title":"ICASSP"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746112.pdf?arnumber=9746112","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T20:10:34Z","timestamp":1660594234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746112\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746112","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}