{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:16:24Z","timestamp":1760710584757,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"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":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413720","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T15:53:45Z","timestamp":1620921225000},"page":"6958-6962","source":"Crossref","is-referenced-by-count":8,"title":["Multilingual Phonetic Dataset for Low Resource Speech Recognition"],"prefix":"10.1109","author":[{"given":"Xinjian","family":"Li","sequence":"first","affiliation":[]},{"given":"David R.","family":"Mortensen","sequence":"additional","affiliation":[]},{"given":"Florian","family":"Metze","sequence":"additional","affiliation":[]},{"given":"Alan W","family":"Black","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"2331","article-title":"Tundra: a multilingual corpus of found data for tts research created with light supervision","author":"stan","year":"2013","journal-title":"InterSpeech"},{"year":"0","article-title":"Free speech recognition (linux, windows and mac) - voxforge.org","key":"ref11"},{"key":"ref12","first-page":"4218","article-title":"Common voice: A massively-multilingual speech corpus","author":"ardila","year":"2020","journal-title":"Proceedings of the 12th Language Resources and Evaluation Conference"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/ICASSP.2019.8683536"},{"key":"ref14","article-title":"Audio-to-text alignment for speech recognition with very limited resources","author":"anguera","year":"2014","journal-title":"Fifteenth Annual Conference of the International Speech Communication Association"},{"key":"ref15","article-title":"A simple and efficient method to align very long speech signals to acoustically imperfect transcriptions","author":"bordel","year":"2012","journal-title":"Thirteenth Annual Conference of the International Speech Communication Association"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1016\/S0167-6393(02)00131-0"},{"key":"ref17","first-page":"3475","article-title":"Panphon: A resource for mapping ipa segments to articulatory feature vectors","author":"mortensen","year":"2016","journal-title":"Proceedings of COLING 2016 the 26th International Conference on Computational Linguistics Technical Papers"},{"year":"0","author":"cieri","article-title":"The fisher corpus: a resource for the next generations of speech-to-text","key":"ref4"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1109\/ICASSP.1992.225858","article-title":"Switchboard: Telephone speech corpus for research and development","volume":"1","author":"godfrey","year":"1992","journal-title":"Acoustics Speech and Signal Processing 1992 ICASSP-92 1992 IEEE International Conference on"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1609\/aaai.v34i05.6341"},{"key":"ref5","first-page":"27403","article-title":"Darpa timit acoustic-phonetic continous speech corpus cd-rom. nist speech disc 1-1.1","volume":"93","author":"garofolo","year":"1993","journal-title":"STIN"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1109\/ICASSP40776.2020.9054362"},{"year":"2009","author":"ladefoged","article-title":"Ucla phonetics lab archive","key":"ref7"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"ref1","first-page":"173","article-title":"Deep speech 2: End-to-end speech recognition in english and mandarin","author":"amodei","year":"2016","journal-title":"International Conference on Machine Learning"},{"year":"2011","author":"harper","article-title":"The iarpa babel multilingual speech database","key":"ref9"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413720.pdf?arnumber=9413720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T11:40:53Z","timestamp":1652182853000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413720\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413720","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}