{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-to-detect-dysarthria-from-raw-speech","title":"Learning to detect dysarthria from raw speech","arxiv_id":"1811.11101","date":"2018-11-27","proceeding":null,"authors":["Juliette Millet","Neil Zeghidour"],"abstract":"Speech classifiers of paralinguistic traits traditionally learn from diverse\nhand-crafted low-level features, by selecting the relevant information for the\ntask at hand. We explore an alternative to this selection, by learning jointly\nthe classifier, and the feature extraction. Recent work on speech recognition\nhas shown improved performance over speech features by learning from the\nwaveform. We extend this approach to paralinguistic classification and propose\na neural network that can learn a filterbank, a normalization factor and a\ncompression power from the raw speech, jointly with the rest of the\narchitecture. We apply this model to dysarthria detection from sentence-level\naudio recordings. Starting from a strong attention-based baseline on which\nmel-filterbanks outperform standard low-level descriptors, we show that\nlearning the filters or the normalization and compression improves over fixed\nfeatures by 10% absolute accuracy. We also observe a gain over OpenSmile\nfeatures by learning jointly the feature extraction, the normalization, and the\ncompression factor with the architecture. This constitutes a first attempt at\nlearning jointly all these operations from raw audio for a speech\nclassification task.","url_abs":"http://arxiv.org/abs/1811.11101v2","url_pdf":"http://arxiv.org/pdf/1811.11101v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-to-detect-dysarthria-from-raw-speech","repo_url":"https://github.com/FastAndFourier/MLA-Project-DYSARTHRIA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"learning-to-detect-dysarthria-from-raw-speech","repo_url":"https://github.com/dkman94/FastrApp-Android","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"learning-to-detect-dysarthria-from-raw-speech","repo_url":"https://github.com/fastrapp/fastr-android-app","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}