{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T10:16:24Z","timestamp":1783160184063,"version":"3.54.6"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12004275"],"award-info":[{"award-number":["12004275"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003398","name":"Shanxi Scholarship Council of China","doi-asserted-by":"publisher","award":["2024\\u2013060"],"award-info":[{"award-number":["2024\\u2013060"]}],"id":[{"id":"10.13039\/501100003398","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017415","name":"Peking University First Hospital","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017415","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000774","name":"Newcastle University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000774","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004480","name":"Shanxi Province Natural Science Foundation","doi-asserted-by":"publisher","award":["202403021211098"],"award-info":[{"award-number":["202403021211098"]}],"id":[{"id":"10.13039\/501100004480","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004311","name":"Shanxi University","doi-asserted-by":"publisher","award":["2025KJ016"],"award-info":[{"award-number":["2025KJ016"]}],"id":[{"id":"10.13039\/501100004311","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Speech Communication"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.specom.2026.103417","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T06:39:06Z","timestamp":1779259146000},"page":"103417","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Pathological speech classification with a dual-branch residual network considering the fluency features of speech expression"],"prefix":"10.1016","volume":"182","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6072-8237","authenticated-orcid":false,"given":"Shufei","family":"Duan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yukai","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zetong","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fujiang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huizhi","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.specom.2026.103417_bib0048","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0287971","article-title":"The Dysarthric Expressed Emotional Database (DEED): an audio-visual database in British English","volume":"18","author":"Alhinti","year":"2023","journal-title":"PLoS. One"},{"issue":"3","key":"10.1016\/j.specom.2026.103417_bib0007","doi-asserted-by":"crossref","DOI":"10.1093\/braincomms\/fcac147","article-title":"The cognitive and neural underpinnings of discourse coherence in post-stroke aphasia","volume":"4","author":"Alyahya","year":"2022","journal-title":"Brain Commun."},{"issue":"4","key":"10.1016\/j.specom.2026.103417_bib0008","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1016\/j.jneuroling.2008.12.001","article-title":"Non-fluent speech in frontotemporal lobar degeneration","volume":"22","author":"Ash","year":"2009","journal-title":"J. Neurolinguistics."},{"key":"10.1016\/j.specom.2026.103417_bib0001","series-title":"2025 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","first-page":"1","article-title":"Pathological voice detection from sustained vowels: handcrafted vs. self-supervised learning","author":"Atmaja","year":"2025"},{"issue":"2","key":"10.1016\/j.specom.2026.103417_bib0034","first-page":"117","article-title":"Speech endpoint detection in low signal-to-noise ratio environments based on mel-frequency cepstral coefficients and short-time energy","volume":"44","author":"Bai","year":"2021","journal-title":"J. Nanjing Norm. Univ. (Nat. Sci. Ed.)"},{"key":"10.1016\/j.specom.2026.103417_bib0036","doi-asserted-by":"crossref","first-page":"34267","DOI":"10.1007\/s11042-025-20616-5","article-title":"Multi-Model emotion recognition from speech using StarGAN, DCNN, and SVM","volume":"84","author":"Banihosseini","year":"2025","journal-title":"Multimed. Tools. Appl."},{"issue":"6","key":"10.1016\/j.specom.2026.103417_bib0010","doi-asserted-by":"crossref","first-page":"2603","DOI":"10.1109\/JBHI.2022.3217559","article-title":"Ensemble approach on deep and handcrafted features for neonatal bowel sound detection","volume":"27","author":"Burne","year":"2023","journal-title":"IEEe J. Biomed. Health Inform."},{"key":"10.1016\/j.specom.2026.103417_bib0014","doi-asserted-by":"crossref","DOI":"10.1038\/s41531-025-00913-4","article-title":"Speech and language biomarkers for Parkinson\u2019s disease prediction, early diagnosis and progression","volume":"11","author":"Cao","year":"2025","journal-title":"npj Parkinsons Disease"},{"issue":"5","key":"10.1016\/j.specom.2026.103417_bib0020","doi-asserted-by":"crossref","first-page":"2489","DOI":"10.1109\/JBHI.2023.3239551","article-title":"E-DGAN: an encoder-decoder generative adversarial network based method for pathological to normal voice conversion","volume":"27","author":"Chu","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"4","key":"10.1016\/j.specom.2026.103417_bib0009","doi-asserted-by":"crossref","first-page":"2083","DOI":"10.1044\/2024_AJSLP-23-00208","article-title":"Connected speech fluency in poststroke and progressive aphasia: a scoping review of quantitative approaches and features","volume":"33","author":"Cordella","year":"2024","journal-title":"Am. J. Speech-Lang. Pathol."},{"issue":"4","key":"10.1016\/j.specom.2026.103417_bib0022","doi-asserted-by":"crossref","first-page":"2083","DOI":"10.1044\/2024_AJSLP-23-00208","article-title":"Connected speech fluency in poststroke and progressive aphasia: a scoping review of quantitative approaches and features","volume":"33","author":"Cordella","year":"2024","journal-title":"Am. J. Speech-Lang. Pathol."},{"issue":"1","key":"10.1016\/j.specom.2026.103417_bib0016","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.jksuci.2012.05.005","article-title":"Assessment of dysarthric speech through rhythm metrics","volume":"25","author":"Dahmani","year":"2013","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"issue":"7","key":"10.1016\/j.specom.2026.103417_bib0027","doi-asserted-by":"crossref","first-page":"5181","DOI":"10.1109\/JBHI.2025.3548917","article-title":"Detection of early Parkinson's disease by leveraging speech Foundation models","volume":"29","author":"Dao","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"3","key":"10.1016\/j.specom.2026.103417_bib0046","first-page":"1588","article-title":"The Whitaker database of dysarthric (cerebral palsy) speech","volume":"93","author":"Deller","year":"1993","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.specom.2026.103417_bib0033","series-title":"Putonghua Yuyinxue Jiaocheng [A Course in Mandarin Phonetics]","author":"Du","year":"2009"},{"key":"10.1016\/j.specom.2026.103417_bib0018","doi-asserted-by":"crossref","first-page":"91057","DOI":"10.1109\/ACCESS.2020.2993856","article-title":"Statistical distribution exploration of tongue movement for pathological articulation on word\/sentence level","volume":"8","author":"Duan","year":"2020","journal-title":"IEEe Access."},{"issue":"1","key":"10.1016\/j.specom.2026.103417_bib0015","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1007\/s10936-019-09676-5","article-title":"Analysis of articulation errors in dysarthric speech","volume":"49","author":"Goswami","year":"2020","journal-title":"J. Psycholinguist. Res."},{"key":"10.1016\/j.specom.2026.103417_bib0029","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.neunet.2021.02.008","article-title":"Residual neural network precisely quantifies dysarthria severity-level based on short-duration speech segments","volume":"139","author":"Gupta","year":"2021","journal-title":"Neural Netw."},{"key":"10.1016\/j.specom.2026.103417_bib0004","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.specom.2020.04.006","article-title":"Analytic phase features for dysarthric speech detection and intelligibility assessment","volume":"121","author":"Gurugubelli","year":"2020","journal-title":"Speech. Commun."},{"key":"10.1016\/j.specom.2026.103417_bib0017","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.specom.2020.09.006","article-title":"Duration of the rhotic approximant \/\u0279\/in spastic dysarthria of different severity levels","volume":"125","author":"Gurugubelli","year":"2020","journal-title":"Speech. Commun."},{"key":"10.1016\/j.specom.2026.103417_bib0037","series-title":"Proc. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.specom.2026.103417_bib0039","doi-asserted-by":"crossref","first-page":"721","DOI":"10.1109\/TASLP.2022.3209941","article-title":"Wnsa-net: an axial-attention-based network for schizophrenia detection using wideband and narrowband spectrograms","volume":"31","author":"He","year":"2022","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"issue":"3","key":"10.1016\/j.specom.2026.103417_bib0025","doi-asserted-by":"crossref","first-page":"2061","DOI":"10.1109\/JBHI.2024.3512417","article-title":"A lightweight deep convolutional neural network extracting local and global contextual features for the classification of Alzheimer's disease using structural MRI","volume":"29","author":"Jabason","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.specom.2026.103417_bib0045","series-title":"Proc. 2023 IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP)","first-page":"1","article-title":"Wav2vec-based detection and severity level classification of dysarthria from speech","author":"Javanmardi","year":"2023"},{"issue":"8","key":"10.1016\/j.specom.2026.103417_bib0019","doi-asserted-by":"crossref","first-page":"4951","DOI":"10.1109\/JBHI.2024.3392829","article-title":"Exploring the impact of fine-tuning the Wav2vec2 model in database-independent detection of dysarthric speech","volume":"28","author":"Javanmardi","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.specom.2026.103417_bib0043","doi-asserted-by":"crossref","DOI":"10.1016\/j.specom.2024.103047","article-title":"Pre-trained models for detection and severity level classification of dysarthria from speech","volume":"158","author":"Javanmardi","year":"2024","journal-title":"Speech. Commun."},{"key":"10.1016\/j.specom.2026.103417_bib0030","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.specom.2022.12.004","article-title":"Dysarthria severity classification using multi-head attention and multi-task learning","volume":"147","author":"Joshy","year":"2023","journal-title":"Speech. Commun."},{"issue":"1","key":"10.1016\/j.specom.2026.103417_bib0002","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1016\/j.csl.2014.02.001","article-title":"Automatic intelligibility classification of sentence-level pathological speech","volume":"29","author":"Kim","year":"2015","journal-title":"Comput. Speech. Lang."},{"key":"10.1016\/j.specom.2026.103417_bib0040","series-title":"Proceedings of the Tenth International Conference on Learning Representations (ICLR 2022), Virtual Event","article-title":"Omni-dimensional dynamic convolution","author":"Li","year":"2022"},{"key":"10.1016\/j.specom.2026.103417_bib0042","series-title":"Proceedings of the 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"6153","article-title":"SCConv: spatial and channel reconstruction convolution for feature redundancy","author":"Li","year":"2023"},{"issue":"4","key":"10.1016\/j.specom.2026.103417_bib0021","doi-asserted-by":"crossref","first-page":"2270","DOI":"10.1109\/JBHI.2023.3340738","article-title":"PVR-vocoder: a pathological voice repair vocoder for voice disorders","volume":"28","author":"Liu","year":"2024","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"11","key":"10.1016\/j.specom.2026.103417_bib0026","doi-asserted-by":"crossref","first-page":"3191","DOI":"10.1109\/JBHI.2020.3011104","article-title":"An efficient deep learning based method for speech assessment of Mandarin-speaking aphasic patients","volume":"24","author":"Mahmoud","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"10.1016\/j.specom.2026.103417_bib0044","doi-asserted-by":"crossref","first-page":"67745","DOI":"10.1109\/ACCESS.2020.2986171","article-title":"Glottal source information for pathological voice detection","volume":"8","author":"Narendra","year":"2020","journal-title":"IEEe Access."},{"key":"10.1016\/j.specom.2026.103417_bib0035","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126854","article-title":"Improved network anomaly detection system using optimized autoencoder \u2212 LSTM","volume":"273","author":"Narmadha","year":"2025","journal-title":"Expert. Syst. Appl."},{"key":"10.1016\/j.specom.2026.103417_bib0041","series-title":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"Efficient multi-scale attention module with cross-spatial learning","author":"Ouyang","year":"2023"},{"key":"10.1016\/j.specom.2026.103417_bib0023","series-title":"In: Proc. Interspeech 2025","first-page":"2138","article-title":"Towards temporally explainable dysarthric speech clarity assessment","author":"Park","year":"2025"},{"issue":"4","key":"10.1016\/j.specom.2026.103417_bib0047","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1007\/s10579-011-9145-0","article-title":"The TORGO database of acoustic and articulatory speech from speakers with dysarthria","volume":"46","author":"Rudzicz","year":"2012","journal-title":"Lang. Resour. Eval."},{"issue":"6","key":"10.1016\/j.specom.2026.103417_bib0013","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.14283\/jpad.2024.132","article-title":"Acoustic speech analysis in Alzheimer\u2019s disease: a systematic review and meta-analysis","volume":"11","author":"Saeedi","year":"2024","journal-title":"J. Prev. Alzheimers. Dis."},{"key":"10.1016\/j.specom.2026.103417_bib0003","first-page":"1","article-title":"Speaker independent dysarthria severity classification using synthesis-based augmentation","author":"Suresh","year":"2025","journal-title":"Int. J. Speech. Technol."},{"issue":"12","key":"10.1016\/j.specom.2026.103417_bib0011","first-page":"11","article-title":"Adult cochlear implant users versus typical hearing persons: an automatic analysis of acoustic-prosodic parameters","volume":"65","author":"Tom\u00e1s","year":"2022","journal-title":"J. Speech. Lang. Hear. Res."},{"issue":"8","key":"10.1016\/j.specom.2026.103417_bib0005","first-page":"979","article-title":"Features of speech prosody function in adult post-stroke non-fluent aphasia patients","volume":"30","author":"Wang","year":"2024","journal-title":"Chin. J. Rehabil. Theory Pract."},{"issue":"4","key":"10.1016\/j.specom.2026.103417_bib0006","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1080\/10255842.2024.2410228","article-title":"Post-stroke dysarthria voice recognition based on fusion feature MSA and 1D","volume":"29","author":"Wujian","year":"2026","journal-title":"Comput. Methods Biomech. Biomed. Eng."},{"issue":"24","key":"10.1016\/j.specom.2026.103417_bib0038","first-page":"79","article-title":"Speech signal recognition and classification based on neural networks","volume":"46","author":"Xue","year":"2023","journal-title":"Mod. Electron. Tech."},{"key":"10.1016\/j.specom.2026.103417_bib0012","first-page":"1","article-title":"Knowledge guided articulatory and spectrum information fusion for obstructive sleep apnea severity estimation","author":"Xue","year":"2025","journal-title":"IEEE J. Biomed. Health Inform. PP"},{"key":"10.1016\/j.specom.2026.103417_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.apacoust.2022.108934","article-title":"A hybrid model for pathological voice recognition of post-stroke dysarthria by using 1DCNN and double-LSTM networks","volume":"197","author":"Ye","year":"2022","journal-title":"Appl. Acoust."},{"issue":"12","key":"10.1016\/j.specom.2026.103417_bib0031","first-page":"140","article-title":"Three-channel pathological speech recognition based on improved feature extraction using LMD","volume":"47","author":"Zhang","year":"2024","journal-title":"Electron. Meas. Technol."},{"key":"10.1016\/j.specom.2026.103417_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130708","article-title":"Multivariate time series approach integrating cross-temporal and cross-channel attention for dysarthria detection from speech","volume":"647","author":"Zhang","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.specom.2026.103417_bib0032","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1109\/TNSRE.2025.3529518","article-title":"Multiangle correlation feature extraction and disease prediction model construction for patients with post-stroke dysarthria","volume":"33","author":"Zhu","year":"2025","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."}],"container-title":["Speech Communication"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000658?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167639326000658?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T09:30:01Z","timestamp":1783157401000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167639326000658"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":48,"alternative-id":["S0167639326000658"],"URL":"https:\/\/doi.org\/10.1016\/j.specom.2026.103417","relation":{},"ISSN":["0167-6393"],"issn-type":[{"value":"0167-6393","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Pathological speech classification with a dual-branch residual network considering the fluency features of speech expression","name":"articletitle","label":"Article Title"},{"value":"Speech Communication","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.specom.2026.103417","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"103417"}}