{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:43:38Z","timestamp":1776883418991,"version":"3.51.2"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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":[[2024,12,1]]},"DOI":"10.1109\/tencon61640.2024.10902687","type":"proceedings-article","created":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T18:40:14Z","timestamp":1741200014000},"page":"469-472","source":"Crossref","is-referenced-by-count":1,"title":["DisfluencySpeech \u2013 Single-Speaker Conversational Speech Dataset with Paralanguage"],"prefix":"10.1109","author":[{"given":"Kyra","family":"Wang","sequence":"first","affiliation":[{"name":"Information Systems Technology and Design, Singapore University of Technology and Design,Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dorien","family":"Herremans","sequence":"additional","affiliation":[{"name":"Information Systems Technology and Design, Singapore University of Technology and Design,Singapore,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5334\/gjgl.1152"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1075\/pc.14.1.08war"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1111\/cogs.12378"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-7687.2011.01049.x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/642611.642662"},{"key":"ref6","volume-title":"A Survey on Neural Speech Synthesis","author":"Tan","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/9781118706664"},{"key":"ref8","first-page":"14610176","author":"Godfrey","year":"1993","journal-title":"Switchboard-1 Release 2"},{"key":"ref9","author":"Ito","year":"2017","journal-title":"The LJ speech dataset"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095751"},{"key":"ref11","first-page":"986","article-title":"DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset","volume-title":"Proc. of the Eighth Int. Joint Conf. on Natural Language Processing (Volume 1: Long Papers)","author":"Li","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016706"},{"key":"ref13","first-page":"17022","article-title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kong","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"ref15","first-page":"97","article-title":"Switchboard SWBD-DAMSL shallow-discourse-function annotation coders manual, draft 13","author":"Jurafsky","year":"1997","journal-title":"University of Colorado, Boulder Institute of Cognitive Science, Boulder, CO, Tech. Rep."},{"key":"ref16","author":"Meteer","journal-title":"Dysfluency Annotation Stylebook for the SAvitchboard Corpus"},{"key":"ref17","article-title":"English (US) ARPA acoustic model v2.0.0","volume-title":"Montreal Forced Aligner","author":"McAuliffe","year":"2022"},{"key":"ref18","article-title":"English (US) ARPA G2P model v2.0.0","volume-title":"Montreal Forced Aligner","author":"McAuliffe","year":"2022"},{"key":"ref19","author":"Ren","year":"2022","journal-title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-demo.17"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref22","author":"Baevski","year":"2020","journal-title":"Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations"},{"key":"ref23","author":"Kuchaiev","year":"2019","journal-title":"NeMo: A toolkit for building AI applications using Neural Modules"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"ref25","first-page":"8067","article-title":"Glow-tts: A generative flow for text-to-speech via monotonic alignment search","volume":"33","author":"Kim","year":"2020","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON)","location":"Singapore, Singapore","start":{"date-parts":[[2024,12,1]]},"end":{"date-parts":[[2024,12,4]]}},"container-title":["TENCON 2024 - 2024 IEEE Region 10 Conference (TENCON)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10902665\/10902666\/10902687.pdf?arnumber=10902687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T06:06:18Z","timestamp":1741241178000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10902687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/tencon61640.2024.10902687","relation":{},"subject":[],"published":{"date-parts":[[2024,12,1]]}}}