{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T16:39:10Z","timestamp":1725727150357},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T00:00:00Z","timestamp":1698710400000},"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":[[2023,10,31]]},"DOI":"10.1109\/apsipaasc58517.2023.10317278","type":"proceedings-article","created":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:07:46Z","timestamp":1700507266000},"page":"2267-2273","source":"Crossref","is-referenced-by-count":0,"title":["Jointly Modelling Transcriptions and Phonemes with Optimal Features to Detect Dementia from Spontaneous Cantonese"],"prefix":"10.1109","author":[{"given":"Xiaoquan","family":"Ke","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Man-Wai","family":"Mak","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Helen M.","family":"Meng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1212\/01.wnl.0000295996.54210.69"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2019.2955022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref4","first-page":"1459","article-title":"openSMILE -the Munich versatile and fast open-source audio feature extractor","volume-title":"Proc. ACM Multimedia Int. Conf","author":"Eyben"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682974"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1572"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414147"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1415"},{"author":"Devlin","key":"ref9","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6428"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1220"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1519"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1850"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2698"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2010-739"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"article-title":"Multi-modal fusion with gating using audio, lexical and disfluency features for Alzheimer\u2019s dementia recognition from spontaneous speech","year":"2021","author":"Rohanian","key":"ref17"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2020-2571","article-title":"Alzheimer\u2019s dementia recognition through spontaneous speech: The ADReSS challenge","author":"Luz","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.01.077"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10122"},{"key":"ref22","first-page":"1299","article-title":"Speaker turn aware similarity scoring for diarization of speech-based cognitive assessments","volume-title":"Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC","author":"Xu"},{"key":"ref23","first-page":"12 449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. neural inf. proces. syst. (NIPS)","author":"Baevski"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1109\/TASLP.2021.3122291","article-title":"HuBERT: Self-supervised speech representation learning by masked prediction of hidden units","author":"Hsu","year":"2021"},{"article-title":"Common voice: A massively-multilingual speech corpus","year":"2020","author":"Ardila","key":"ref25"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1582"}],"event":{"name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","start":{"date-parts":[[2023,10,31]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2023,11,3]]}},"container-title":["2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10317071\/10317095\/10317278.pdf?arnumber=10317278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T18:50:00Z","timestamp":1709405400000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10317278\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,31]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/apsipaasc58517.2023.10317278","relation":{},"subject":[],"published":{"date-parts":[[2023,10,31]]}}}