{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,6]],"date-time":"2025-07-06T00:05:40Z","timestamp":1751760340148,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,11,1]],"date-time":"2022-11-01T00:00:00Z","timestamp":1667260800000},"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":[[2022,11]]},"DOI":"10.1109\/o-cocosda202257103.2022.9997860","type":"proceedings-article","created":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T18:48:53Z","timestamp":1672253333000},"page":"1-5","source":"Crossref","is-referenced-by-count":5,"title":["The Speech Labeling and Modeling Toolkit (SLMTK) Version 1.0"],"prefix":"10.1109","author":[{"given":"Chen-Yu","family":"Chiang","sequence":"first","affiliation":[{"name":"National Taipei University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu-Hao","family":"Li","sequence":"additional","affiliation":[{"name":"National Taipei University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yen-Ting","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taipei University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jia-Jyu","family":"Su","sequence":"additional","affiliation":[{"name":"National Taipei University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Cheng","family":"Chen","sequence":"additional","affiliation":[{"name":"AcoustInTek Co., Ltd,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng-Che","family":"Kao","sequence":"additional","affiliation":[{"name":"AcoustInTek Co., Ltd,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shu-Lei","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taipei University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pin-Han","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taipei University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shao-Wei","family":"Hong","sequence":"additional","affiliation":[{"name":"National Taipei University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guan-Ting","family":"Liou","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen-Yang","family":"Chang","sequence":"additional","affiliation":[{"name":"AcoustInTek Co., Ltd,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jen-Chieh","family":"Chiang","sequence":"additional","affiliation":[{"name":"AcoustInTek Co., Ltd,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yen-Ting","family":"Lin","sequence":"additional","affiliation":[{"name":"udnDigital Co., Ltd,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yih-Ru","family":"Wang","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sin-Horng","family":"Chen","sequence":"additional","affiliation":[{"name":"National Yang Ming Chiao Tung University,Taiwan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"TextGrid file formats"},{"key":"ref2","article-title":"Development of a Smart Sclerosis Communication System for Patients with ALS: Outcome Add-On and Application","author":"Liu","year":"2021","journal-title":"Ministry of Science and Technology"},{"article-title":"Revoice Project Taiwan","year":"2022","author":"Chiang","key":"ref3"},{"journal-title":"prepared to submit to Augmentative and Alternative Communication","article-title":"Project Save and Sound: Constructing Personalized Mandarin Text-to-Speech Systems for ALS Patients","author":"Chiang","key":"ref4"},{"article-title":"On the Interaction between L1 Transfer and Universal Constraints\u2013Evidence from the Acquisition of Mandarin Tones by French Speakers","volume-title":"submitted at the North American Conference on Chinese Linguistics","author":"Huang","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2762432"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icsda.2014.7051427"},{"key":"ref8","article-title":"Prosody Hierarchy Construction for Mixed Chinese-English Spelling Speech and its Application to TTS","author":"Tsai","year":"2010","journal-title":"National Chiao Tung University"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2018-120"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1214"},{"article-title":"Method of generating estimated value of local inverse speaking rate (ISR) and device and method of generating predicted value of local ISR accordingly","year":"2021","author":"Chiang","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2598307"},{"author":"Boersma","key":"ref13","article-title":"Praat: doing phonetics by computer. 2022.[Online]"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2004-1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/992628.992631"},{"article-title":"CRF++: Yet another CRF toolkit","year":"2013","author":"Kudo","key":"ref17"},{"key":"ref18","first-page":"1","article-title":"Traditional Chinese parser and language modeling for Mandarin ASR","author":"Lin","year":"2013","journal-title":"2013 O-COCOSDA\/CASLRE"},{"key":"ref19","article-title":"Part of speech (POS) analysis on Chinese language","volume-title":"Technical Report, the Institute of Information Science, Academia Sinica, ROC","author":"Chang","year":"1989"},{"key":"ref20","first-page":"115","article-title":"A Mandarin-English Mixed TTS Constructed by Independent Mandarin and English Corpora","author":"Chang","year":"2017","journal-title":"20th O-COCOSDA 2017"},{"article-title":"A Study on Polyphone Disambiguation and Tone 3 Sandhi Labeling for Traditional Chinese","volume-title":"presented at the 17th International Conference Oriental COCOSDA","author":"Liou","key":"ref21"},{"key":"ref22","first-page":"518","article-title":"A robust algorithm for pitch tracking (RAPT)","volume":"495","author":"Talkin","year":"1995","journal-title":"Speech coding and synthesis"},{"key":"ref23","article-title":"HTK speech recognition toolkit"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/26.61370"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.366990"},{"key":"ref26","article-title":"Tone Recognition Using MLP and Prosody Model","author":"Chen","year":"2007","journal-title":"National Chiao Tung University"},{"article-title":"HMM\/DNN-based Speech Synthesis System (HTS)","year":"2012","author":"Oura","key":"ref27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2006647"},{"key":"ref29","article-title":"Neural Speech Synthesis with Transformer Network","author":"Li","year":"2019","journal-title":"arXiv:1809.08895[cs]"},{"key":"ref30","article-title":"Tacotron: Towards End-to-End Speech Synthesis","author":"Wang","year":"2017","journal-title":"arXiv:1703.10135[cs]"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref32","article-title":"FastSpeech: Fast, Robust and Controllable Text to Speech","author":"Ren","year":"2019","journal-title":"arXiv:1905.09263[cs, eess]"},{"key":"ref33","article-title":"Fastspeech 2: Fast and high-quality end-to-end text to speech","author":"Ren","year":"2020","journal-title":"arXiv preprint arXiv:2006.04558"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"article-title":"The Kaldi Speech Recognition Toolkit","year":"2011","author":"Povey","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-021-01365-x"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023283"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3016564"},{"key":"ref39","article-title":"Probing the phonetic and phonological knowledge of tones in Mandarin TTS models","author":"Zhu","year":"2019","journal-title":"arXiv:1912.10915[cs, eess]"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682368"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1121\/1.5099263"}],"event":{"name":"2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","start":{"date-parts":[[2022,11,24]]},"location":"Hanoi, Vietnam","end":{"date-parts":[[2022,11,26]]}},"container-title":["2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9997569\/9997817\/09997860.pdf?arnumber=9997860","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T12:21:43Z","timestamp":1709382103000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9997860\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/o-cocosda202257103.2022.9997860","relation":{},"subject":[],"published":{"date-parts":[[2022,11]]}}}