{"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/fully-supervised-speaker-diarization","title":"Fully Supervised Speaker Diarization","arxiv_id":"1810.04719","date":"2018-10-10","proceeding":null,"authors":["Aonan Zhang","Quan Wang","Zhenyao Zhu","John Paisley","Chong Wang"],"abstract":"In this paper, we propose a fully supervised speaker diarization approach,\nnamed unbounded interleaved-state recurrent neural networks (UIS-RNN). Given\nextracted speaker-discriminative embeddings (a.k.a. d-vectors) from input\nutterances, each individual speaker is modeled by a parameter-sharing RNN,\nwhile the RNN states for different speakers interleave in the time domain. This\nRNN is naturally integrated with a distance-dependent Chinese restaurant\nprocess (ddCRP) to accommodate an unknown number of speakers. Our system is\nfully supervised and is able to learn from examples where time-stamped speaker\nlabels are annotated. We achieved a 7.6% diarization error rate on NIST SRE\n2000 CALLHOME, which is better than the state-of-the-art method using spectral\nclustering. Moreover, our method decodes in an online fashion while most\nstate-of-the-art systems rely on offline clustering.","url_abs":"http://arxiv.org/abs/1810.04719v7","url_pdf":"http://arxiv.org/pdf/1810.04719v7.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":"fully-supervised-speaker-diarization","repo_url":"https://github.com/google/uis-rnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"speaker-diarization","task_name":"Speaker Diarization"},{"task_slug":"speaker-diarization","task_name":"speaker-diarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speaker-diarization-on-hub5-00-callhome","task":"Speaker Diarization","dataset":"Hub5'00 CallHome","model":"UIS-RNN","rank_in_archive_order":1,"of":1,"metrics":{"V":"10.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.04719","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}