{"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/yolo-stutter-end-to-end-region-wise-speech","title":"YOLO-Stutter: End-to-end Region-Wise Speech Dysfluency Detection","arxiv_id":"2408.15297","date":"2024-08-27","proceeding":null,"authors":["Xuanru Zhou","Anshul Kashyap","Steve Li","Ayati Sharma","Brittany Morin","David Baquirin","Jet Vonk","Zoe Ezzes","Zachary Miller","Maria Luisa Gorno Tempini","Jiachen Lian","Gopala Krishna Anumanchipalli"],"abstract":"Dysfluent speech detection is the bottleneck for disordered speech analysis and spoken language learning. Current state-of-the-art models are governed by rule-based systems which lack efficiency and robustness, and are sensitive to template design. In this paper, we propose YOLO-Stutter: a first end-to-end method that detects dysfluencies in a time-accurate manner. YOLO-Stutter takes imperfect speech-text alignment as input, followed by a spatial feature aggregator, and a temporal dependency extractor to perform region-wise boundary and class predictions. We also introduce two dysfluency corpus, VCTK-Stutter and VCTK-TTS, that simulate natural spoken dysfluencies including repetition, block, missing, replacement, and prolongation. Our end-to-end method achieves state-of-the-art performance with a minimum number of trainable parameters for on both simulated data and real aphasia speech. Code and datasets are open-sourced at https://github.com/rorizzz/YOLO-Stutter","url_abs":"https://arxiv.org/abs/2408.15297v3","url_pdf":"https://arxiv.org/pdf/2408.15297v3.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":"yolo-stutter-end-to-end-region-wise-speech","repo_url":"https://github.com/rorizzz/yolo-stutter","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2408.15297","atlas_url":"https://app.syntology.ai/?focus=2408.15297","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15297"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rorizzz/yolo-stutter","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran":2,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"59ae0708b1e8d94b","entry":"convert_pad_shape","repo":"rorizzz/yolo-stutter","repo_kind":"official","path":"yolo-stutter/utils/vits/commons.py","file_url":"https://github.com/rorizzz/yolo-stutter/blob/HEAD/yolo-stutter/utils/vits/commons.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"code_sha256_prefix":"a26f85d7c72ef39a","entry":"get_padding","repo":"rorizzz/yolo-stutter","repo_kind":"official","path":"yolo-stutter/utils/vits/commons.py","file_url":"https://github.com/rorizzz/yolo-stutter/blob/HEAD/yolo-stutter/utils/vits/commons.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a26f85d7c72ef39a"}},{"code_sha256_prefix":"55b57dbda68f807e","entry":"get_sample_rate_wave","repo":"rorizzz/yolo-stutter","repo_kind":"official","path":"yolo-stutter/etc/inference.py","file_url":"https://github.com/rorizzz/yolo-stutter/blob/HEAD/yolo-stutter/etc/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"55b57dbda68f807e"}},{"code_sha256_prefix":"2a1a83e3efb39fb0","entry":"print_shapes","repo":"rorizzz/yolo-stutter","repo_kind":"official","path":"yolo-stutter/utils/model_utils/check_dims.py","file_url":"https://github.com/rorizzz/yolo-stutter/blob/HEAD/yolo-stutter/utils/model_utils/check_dims.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a1a83e3efb39fb0"}},{"code_sha256_prefix":"c01a3efb274ff778","entry":"intersperse","repo":"rorizzz/yolo-stutter","repo_kind":"official","path":"yolo-stutter/utils/vits/commons.py","file_url":"https://github.com/rorizzz/yolo-stutter/blob/HEAD/yolo-stutter/utils/vits/commons.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c01a3efb274ff778"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}