{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T09:39:42Z","timestamp":1782380382275,"version":"3.54.5"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T00:00:00Z","timestamp":1705363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Speaker diarization is an essential preprocessing step for diagnosing cognitive impairments from speech-based Montreal cognitive assessments (MoCA).<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This paper proposes three enhancements to the conventional speaker diarization methods for such assessments. The enhancements tackle the challenges of diarizing MoCA recordings on two fronts. First, multi-scale channel interdependence speaker embedding is used as the front-end speaker representation for overcoming the acoustic mismatch caused by far-field microphones. Specifically, a squeeze-and-excitation (SE) unit and channel-dependent attention are added to Res2Net blocks for multi-scale feature aggregation. Second, a sequence comparison approach with a holistic view of the whole conversation is applied to measure the similarity of short speech segments in the conversation, which results in a speaker-turn aware scoring matrix for the subsequent clustering step. Third, to further enhance the diarization performance, we propose incorporating a pairwise similarity measure so that the speaker-turn aware scoring matrix contains both local and global information across the segments.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Evaluations on an interactive MoCA dataset show that the proposed enhancements lead to a diarization system that outperforms the conventional x-vector\/PLDA systems under language-, age-, and microphone-mismatch scenarios.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The results also show that the proposed enhancements can help hypothesize the speaker-turn timestamps, making the diarization method amendable to datasets without timestamp information.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnins.2023.1351848","type":"journal-article","created":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T04:26:41Z","timestamp":1705379201000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Speaker-turn aware diarization for speech-based cognitive assessments"],"prefix":"10.3389","volume":"17","author":[{"given":"Sean Shensheng","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoquan","family":"Ke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Man-Wai","family":"Mak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ka Ho","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helen","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timothy C. Y.","family":"Kwok","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunqi","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,1,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1109\/TASL.2011.2125954","article-title":"Speaker diarization: a review of recent research","volume":"20","author":"Anguera","year":"2012","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1021","DOI":"10.1002\/1099-1166(200011)15:11&lt;1021::AID-GPS234&gt;3.0.CO;2-6","article-title":"The mini-Cog: a cognitive \u2018vital signs' measure for dementia screening in multi-lingual elderly","volume":"15","author":"Borson","year":"2000","journal-title":"Int. J. Geriatr. Psychiatry"},{"key":"B3","doi-asserted-by":"publisher","first-page":"e10966","DOI":"10.1186\/s13195-016-0176-z","article-title":"Mini mental state examination and logical memory scores for entry into Alzheimer's disease trials","volume":"8","author":"Chapman","year":"2016","journal-title":"Medicine"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.12740\/PP\/45368","article-title":"Is the Montreal cognitive assessment (MoCA) test better suited than the mini-mental state examination (MMSE) in mild cognitive impairment (MCI) detection among people aged over 60? meta-analysis","volume":"50","author":"Ciesielska","year":"2016","journal-title":"Psychiatr. Pol"},{"key":"B5","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1192\/bjp.bp.113.127811","article-title":"Treatment for mild cognitive impairment: systematic review","volume":"203","author":"Cooper","year":"2013","journal-title":"Br. J. Psychiatry"},{"key":"B6","first-page":"3830","article-title":"\u201cECAPA-TDNN: emphasized channel attention, propagation and aggregation in TDNN based speaker verification,\u201d","volume-title":"Proceedings of Interspeech","author":"Desplanques","year":"2020"},{"key":"B7","first-page":"346","article-title":"\u201cBayesian HMM based x-vector clustering for speaker diarization,\u201d","volume-title":"Proceedings of Interspeech","author":"Diez","year":"2019"},{"key":"B8","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","article-title":"The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing","volume":"7","author":"Eyben","year":"2016","journal-title":"IEEE Trans. Affect. Comput"},{"key":"B9","first-page":"1459","article-title":"\u201cOpenSMILE - the Munich versatile and fast open-source audio feature extractor,\u201d","volume-title":"Proceedings of ACM Multimedia International Conference","author":"Eyben","year":"2010"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD010860.pub2","article-title":"Mini-Cog for the diagnosis of Alzheimer's disease dementia and other dementias within a community setting","author":"Fage","year":"2015","journal-title":"Cochrane Database Syst. Rev"},{"key":"B11","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/11965152_28","article-title":"\u201cThe rich transcription 2006 spring meeting recognition evaluation,\u201d","volume-title":"International Workshop on Machine Learning for Multimodal Interaction","author":"Fiscus","year":"2006"},{"key":"B12","first-page":"369","article-title":"\u201cThe rich transcription 2005 spring meeting recognition evaluation,\u201d","volume-title":"Proceedings of MLMI","author":"Fiscus","year":"2005"},{"key":"B13","doi-asserted-by":"crossref","first-page":"249","DOI":"10.21437\/Interspeech.2011-53","article-title":"\u201cAnalysis of i-vector length normalization in speaker recognition systems,\u201d","volume-title":"Proceedings of Interspeech","author":"Garcia-Romero","year":"2011"},{"key":"B14","first-page":"4930","article-title":"\u201cSpeaker diarization using deep neural network embeddings,\u201d","volume-title":"Proceedings of ICASSP","author":"Garcia-Romero","year":"2017"},{"key":"B15","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1109\/JSTSP.2019.2955022","article-title":"An assessment of paralinguistic acoustic features for detection of Alzheimer's dementia in spontaneous speech","volume":"14","author":"Haider","year":"2020","journal-title":"IEEE J. Sel. Top. Signal Process"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1590","DOI":"10.1109\/TASL.2008.2002085","article-title":"Strategies to improve the robustness of agglomerative hierarchical clustering under data source variation for speaker diarization","volume":"16","author":"Han","year":"2008","journal-title":"IEEE Trans. Audio Speech Lang. Process"},{"key":"B17","first-page":"7132","article-title":"\u201cSqueeze-and-excitation networks,\u201d","volume-title":"Proceedings of IEEE CVPR","author":"Hu","year":"2018"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1508.01991","article-title":"Bidirectional LSTM-CRF models for sequence tagging","author":"Huang","year":"2015","journal-title":"arXiv:1508.01991"},{"key":"B19","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/11744085_41","article-title":"\u201cProbabilistic linear discriminant analysis,\u201d","author":"Ioffe","year":"2006","journal-title":"European Conference on Computer Vision"},{"key":"B20","first-page":"4986","article-title":"\u201cSpeaker clustering using vector quantization and spectral clustering,\u201d","volume-title":"Proceedings of ICASSP","author":"Iso","year":"2010"},{"key":"B21","first-page":"1","article-title":"\u201cIn search of strong embedding extractors for speaker diarisation,\u201d","volume-title":"Proceedings of ICASSP 2023","author":"Jung","year":"2023"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1519","DOI":"10.1212\/WNL.0b013e3181a2e864","article-title":"Risk of dementia in MCI: combined effect of cerebrovascular disease, volumetric MRI, and 1H MRS","volume":"72","author":"Kantarci","year":"2009","journal-title":"Neurology"},{"key":"B23","doi-asserted-by":"crossref","first-page":"2153","DOI":"10.21437\/Interspeech.2022-10122","article-title":"\u201cAutomatic selection of discriminative features for dementia detection in cantonese-speaking people,\u201d","volume-title":"Proceedings of Interspeech","author":"Ke","year":"2022"},{"key":"B24","doi-asserted-by":"publisher","first-page":"5220","DOI":"10.1109\/ICASSP.2017.7953152","article-title":"\u201cA study on data augmentation of reverberant speech for robust speech recognition,\u201d","author":"Ko","year":"2017","journal-title":"Proceedings"},{"key":"B25","doi-asserted-by":"publisher","first-page":"120","DOI":"10.2174\/1567205014666170829111942","article-title":"Use of speech analyses within a mobile application for the assessment of cognitive impairment in elderly people","volume":"15","author":"Konig","year":"2018","journal-title":"Curr. Alzheimer Res"},{"key":"B26","first-page":"366","article-title":"\u201cLSTM based similarity measurement with spectral clustering for speaker diarization,\u201d","volume-title":"Proceedings of Interspeech","author":"Lin","year":"2019"},{"key":"B27","doi-asserted-by":"publisher","first-page":"2810","DOI":"10.1109\/TASLP.2020.3030499","article-title":"A framework for adapting DNN speaker embedding across languages","volume":"28","author":"Lin","year":"2020","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process"},{"key":"B28","doi-asserted-by":"publisher","first-page":"968","DOI":"10.1109\/TASLP.2022.3153270","article-title":"Mixture representation learning for deep speaker embedding","volume":"30","author":"Lin","year":"2022","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1909","article-title":"End-to-end neural diarization: from transformer to conformer","author":"Liu","year":"2021","journal-title":"arXiv:2106.07167"},{"key":"B30","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/s11222-007-9033-z","article-title":"A tutorial on spectral clustering","volume":"17","author":"Luxburg","year":"2007","journal-title":"Stat. Comput"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2571","article-title":"Alzheimer's dementia recognition through spontaneous speech: the ADReSS challenge","author":"Luz","year":"2020","journal-title":"arXiv:2004.06833"},{"key":"B32","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1017\/9781108552332","author":"Mak","year":"2020","journal-title":"Machine Learning for Speaker Recognition"},{"key":"B34","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1080\/13803395.2018.1446513","article-title":"Connected speech and language in mild cognitive impairment and Alzheimer's disease: a review of picture description tasks","volume":"40","author":"Mueller","year":"2018","journal-title":"J. Clin. Exp. Neuropsychol"},{"key":"B35","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1111\/j.1532-5415.2005.53221.x","article-title":"The Montreal cognitive assessment, MoCA: a brief screening tool for mild cognitive impairment","volume":"53","author":"Nasreddine","year":"2005","journal-title":"J. Am. Geriatr. Soc"},{"key":"B36","doi-asserted-by":"crossref","first-page":"2178","DOI":"10.21437\/Interspeech.2006-566","article-title":"\u201cA spectral clustering approach to speaker diarization,\u201d","volume-title":"Proceedings of Interspeech","author":"Ning","year":"2006"},{"key":"B37","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.patcog.2009.06.001","article-title":"Incremental spectral clustering by efficiently updating the eigen-system","volume":"43","author":"Ning","year":"2010","journal-title":"Pattern Recogn"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993","article-title":"Attentive statistics pooling for deep speaker embedding","author":"Okabe","year":"2018","journal-title":"arXiv:1803.10963"},{"key":"B39","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1053\/apnr.2000.9231","article-title":"An examination of psychometric properties of the mini-mental state examination and the standardized mini-mental state examination: implications for clinical practice","volume":"13","author":"Pangman","year":"2000","journal-title":"Appl. Nurs. Res"},{"key":"B40","article-title":"\u201cThe Kaldi speech recognition toolkit,\u201d","volume-title":"Proceedings of the Automatic Speech Recognition and Understanding Workshop","author":"Povey","year":"2011"},{"key":"B41","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/S0140-6736(17)31757-9","article-title":"Progress on dementia?leaving no one behind","volume":"390","author":"Prince","year":"2017","journal-title":"Lancet"},{"key":"B42","first-page":"1","article-title":"\u201cProbabilistic linear discriminant analysis for inferences about identity,\u201d","volume-title":"Proceedings of ICCV","author":"Prince","year":"2007"},{"key":"B43","unstructured":"QinY.\n            LiuW.\n            PengZ.\n            NgS.\n            LiJ.\n            HuH.\n          Exploiting pre-trained ASR models for Alzheimer's disease recognition through spontaneous speech. arXiv:2110.014932021"},{"key":"B44","doi-asserted-by":"crossref","first-page":"2794","DOI":"10.21437\/Interspeech.2010-739","article-title":"\u201cThe INTERSPEECH 2010 paralinguistic challenge,\u201d","volume-title":"Proceedings of Interspeech","author":"Schuller","year":"2010"},{"key":"B45","unstructured":"SnyderD.\n            ChenG.\n            PoveyD.\n          Musan: a music, speech, and noise corpus. arXiv:1510.08484v12015"},{"key":"B46","doi-asserted-by":"crossref","first-page":"999","DOI":"10.21437\/Interspeech.2017-620","article-title":"\u201cDeep neural network embeddings for text-independent speaker verification,\u201d","volume-title":"Proceedings of Interspeech","author":"Snyder","year":"2017"},{"key":"B47","first-page":"5329","article-title":"\u201cX-vectors: robust DNN embeddings for speaker recognition,\u201d","volume-title":"Proceedings of ICASSP","author":"Snyder","year":"2018"},{"key":"B48","first-page":"1652","article-title":"\u201cMargin matters: towards more discriminative deep neural network embeddings for speaker recognition,\u201d","volume-title":"Proceedings of IEEE APSIPA","author":"Xiang","year":"2019"},{"key":"B49","doi-asserted-by":"crossref","DOI":"10.1109\/ISCSLP49672.2021.9362084","article-title":"\u201cAge-invariant speaker embedding for diarization of cognitive assessments,\u201d","volume-title":"Proceedings of ISCSLP","author":"Xu","year":""},{"key":"B50","unstructured":"\u201cSpeaker turn aware similarity scoring for diarization of speech-based cognitive assessments,\u201d12991304\n            XuS. S.\n            MakM. W.\n            WongK. H.\n            MengH.\n            KwokT. C. Y.\n          Proceedings of APSIPA"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.12592","article-title":"BUT system description to VoxCeleb speaker recognition challenge 2019","author":"Zeinali","year":"2019","journal-title":"arXiv:1910.12592"},{"key":"B52","doi-asserted-by":"crossref","DOI":"10.1109\/ISCSLP49672.2021.9362108","article-title":"\u201cChannel interdependence enhanced speaker embeddings for far-field speaker verification,\u201d","volume-title":"Proceedings of ISCSLP","author":"Zhao","year":"2021"},{"key":"B53","first-page":"3573","article-title":"\u201cSelf-attentive speaker embeddings for text-independent speaker verification,\u201d","volume-title":"Proceedings of Interspeech","author":"Zhu","year":"2018"}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2023.1351848\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,16]],"date-time":"2024-01-16T04:26:50Z","timestamp":1705379210000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2023.1351848\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,16]]},"references-count":53,"alternative-id":["10.3389\/fnins.2023.1351848"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2023.1351848","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,16]]},"article-number":"1351848"}}