{"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/bayesian-hmm-clustering-of-x-vector-sequences","title":"Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks","arxiv_id":"2012.14952","date":"2020-12-29","proceeding":null,"authors":["Federico Landini","Ján Profant","Mireia Diez","Lukáš Burget"],"abstract":"The recently proposed VBx diarization method uses a Bayesian hidden Markov model to find speaker clusters in a sequence of x-vectors. In this work we perform an extensive comparison of performance of the VBx diarization with other approaches in the literature and we show that VBx achieves superior performance on three of the most popular datasets for evaluating diarization: CALLHOME, AMI and DIHARDII datasets. Further, we present for the first time the derivation and update formulae for the VBx model, focusing on the efficiency and simplicity of this model as compared to the previous and more complex BHMM model working on frame-by-frame standard Cepstral features. Together with this publication, we release the recipe for training the x-vector extractors used in our experiments on both wide and narrowband data, and the VBx recipes that attain state-of-the-art performance on all three datasets. Besides, we point out the lack of a standardized evaluation protocol for AMI dataset and we propose a new protocol for both Beamformed and Mix-Headset audios based on the official AMI partitions and transcriptions.","url_abs":"https://arxiv.org/abs/2012.14952v1","url_pdf":"https://arxiv.org/pdf/2012.14952v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"bayesian-hmm-clustering-of-x-vector-sequences","repo_url":"https://github.com/BUTSpeechFIT/AMI-diarization-setup","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"bayesian-hmm-clustering-of-x-vector-sequences","repo_url":"https://github.com/BUTSpeechFIT/VBx","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"bayesian-hmm-clustering-of-x-vector-sequences","repo_url":"https://github.com/phonexiaresearch/VBx-training-recipe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"bayesian-hmm-clustering-of-x-vector-sequences","repo_url":"https://github.com/hltcoe/VBx","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"bayesian-hmm-clustering-of-x-vector-sequences","repo_url":"https://github.com/pyannote/ami-diarization-setup","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2012.14952","atlas_url":"https://app.syntology.ai/?focus=2012.14952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.14952"}},"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/phonexiaresearch/VBx-training-recipe","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hltcoe/VBx","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pyannote/ami-diarization-setup","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BUTSpeechFIT/VBx","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BUTSpeechFIT/AMI-diarization-setup","reach":{"status":"unanswered"}}],"summary":{"ran_fixture":2,"ran_draft_wrong":2,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":1},"listed":{"samples":3,"ran":1,"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":6,"samples":[{"code_sha256_prefix":"1f5f24ae84241edc","entry":"DER","repo":"BUTSpeechFIT/VBx","repo_kind":"official","path":"VBx/VBx.py","file_url":"https://github.com/BUTSpeechFIT/VBx/blob/HEAD/VBx/VBx.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1f5f24ae84241edc"}},{"code_sha256_prefix":"09ed78b77685499e","entry":"VBx","repo":"BUTSpeechFIT/VBx","repo_kind":"official","path":"VBx/VBx.py","file_url":"https://github.com/BUTSpeechFIT/VBx/blob/HEAD/VBx/VBx.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"09ed78b77685499e"}},{"code_sha256_prefix":"259e6f64ed883164","entry":"forward_backward","repo":"BUTSpeechFIT/VBx","repo_kind":"official","path":"VBx/VBx.py","file_url":"https://github.com/BUTSpeechFIT/VBx/blob/HEAD/VBx/VBx.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"259e6f64ed883164"}},{"code_sha256_prefix":"b331ed6ad2fffb96","entry":"frame_labels2posterior_mx","repo":"hltcoe/VBx","repo_kind":"listed","path":"VBx/VB_diarization.py","file_url":"https://github.com/hltcoe/VBx/blob/HEAD/VBx/VB_diarization.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b331ed6ad2fffb96"}},{"code_sha256_prefix":"6ea546d219816cd8","entry":"VB_diarization","repo":"hltcoe/VBx","repo_kind":"listed","path":"VBx/VB_diarization.py","file_url":"https://github.com/hltcoe/VBx/blob/HEAD/VBx/VB_diarization.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6ea546d219816cd8"}},{"code_sha256_prefix":"8948ed6f7ec7197a","entry":"precalculate_VtiEV","repo":"hltcoe/VBx","repo_kind":"listed","path":"VBx/VB_diarization.py","file_url":"https://github.com/hltcoe/VBx/blob/HEAD/VBx/VB_diarization.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8948ed6f7ec7197a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}