{"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/told-a-novel-two-stage-overlap-aware","title":"TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization","arxiv_id":"2303.05397","date":"2023-03-08","proceeding":null,"authors":["JiaMing Wang","Zhihao Du","Shiliang Zhang"],"abstract":"Recently, end-to-end neural diarization (EEND) is introduced and achieves promising results in speaker-overlapped scenarios. In EEND, speaker diarization is formulated as a multi-label prediction problem, where speaker activities are estimated independently and their dependency are not well considered. To overcome these disadvantages, we employ the power set encoding to reformulate speaker diarization as a single-label classification problem and propose the overlap-aware EEND (EEND-OLA) model, in which speaker overlaps and dependency can be modeled explicitly. Inspired by the success of two-stage hybrid systems, we further propose a novel Two-stage OverLap-aware Diarization framework (TOLD) by involving a speaker overlap-aware post-processing (SOAP) model to iteratively refine the diarization results of EEND-OLA. Experimental results show that, compared with the original EEND, the proposed EEND-OLA achieves a 14.39% relative improvement in terms of diarization error rates (DER), and utilizing SOAP provides another 19.33% relative improvement. As a result, our method TOLD achieves a DER of 10.14% on the CALLHOME dataset, which is a new state-of-the-art result on this benchmark to the best of our knowledge.","url_abs":"https://arxiv.org/abs/2303.05397v2","url_pdf":"https://arxiv.org/pdf/2303.05397v2.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":"told-a-novel-two-stage-overlap-aware","repo_url":"https://github.com/alibaba-damo-academy/FunASR","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"speaker-diarization","task_name":"Speaker Diarization"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"},{"task_slug":"speaker-diarization","task_name":"speaker-diarization"}],"methods":[{"method_slug":"eend","method_name":"EEND"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speaker-diarization-on-callhome","task":"Speaker Diarization","dataset":"CALLHOME","model":"TOLD","rank_in_archive_order":1,"of":10,"metrics":{"CF":"2.94","DER(%)":"10.14","DER(ig olp)":"7.37","FA":"2.4","MI":"4.8"},"uses_additional_data":false},{"leaderboard":"/sota/speaker-diarization-on-callhome","task":"Speaker Diarization","dataset":"CALLHOME","model":"EEND-OLA","rank_in_archive_order":3,"of":10,"metrics":{"DER(%)":"12.57","DER(ig olp)":"9.14"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}