{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/speaker-diarization/papers/4","list_of":"/task/speaker-diarization","task":"Speaker Diarization","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":4,"pages_in_order":4,"rows_per_page":100,"rows":[301,328],"of":328,"counts":{"archive_papers_tagged":328,"with_a_code_link":93,"where_syntology_ran_a_sample":14,"not_listed_spam_title":0,"listed":328,"listed_where_code_ran":14,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":3,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":3,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/speaker-diarization","prev":"/task/speaker-diarization/papers/3","next":null,"papers":[{"url":null,"slug":"designing-an-effective-metric-learning","title":"Designing an Effective Metric Learning Pipeline for Speaker Diarization","date":"2018-11-01","arxiv_id":"1811.00183","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-acoustic-model-training-for","title":"Semi-supervised acoustic model training for speech with code-switching","date":"2018-10-23","arxiv_id":"1810.09699","repositories_listed":0,"syntology":null},{"url":null,"slug":"triplet-network-with-attention-for-speaker","title":"Triplet Network with Attention for Speaker Diarization","date":"2018-08-04","arxiv_id":"1808.01535","repositories_listed":0,"syntology":null},{"url":null,"slug":"indigenous-language-technologies-in-canada","title":"Indigenous language technologies in Canada: Assessment, challenges, and successes","date":"2018-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"weakly-supervised-training-of-speaker","title":"Weakly Supervised Training of Speaker Identification Models","date":"2018-06-22","arxiv_id":"1806.08621","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-automated-medical-scribe-for-documenting","title":"An automated medical scribe for documenting clinical encounters","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"role-specific-language-models-for-processing","title":"Role-specific Language Models for Processing Recorded Neuropsychological Exams","date":"2018-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-speaker-segmentation-and","title":"Multimodal Speaker Segmentation and Diarization using Lexical and Acoustic Cues via Sequence to Sequence Neural Networks","date":"2018-05-28","arxiv_id":"1805.10731","repositories_listed":0,"syntology":null},{"url":null,"slug":"computer-assisted-speaker-diarization-how-to","title":"Computer-assisted Speaker Diarization: How to Evaluate Human Corrections","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"matics-software-suite-new-tools-for","title":"Matics Software Suite: New Tools for Evaluation and Data Exploration","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"ao14i-vectorepldaa-a12c-gmm","title":"基於i-vector與PLDA並使用GMM-HMM強制對位之自動語者分段標記系統 (Speaker Diarization based on I-vector PLDA Scoring and using GMM-HMM Forced Alignment) [In Chinese]","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-diarization-using-deep-recurrent","title":"Speaker Diarization using Deep Recurrent Convolutional Neural Networks for Speaker Embeddings","date":"2017-08-09","arxiv_id":"1708.02840","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-infinite-hidden-markov-model-with","title":"An Infinite Hidden Markov Model With Similarity-Biased Transitions","date":"2017-07-21","arxiv_id":"1707.06756","repositories_listed":0,"syntology":null},{"url":null,"slug":"polish-read-speech-corpus-for-speech-tools","title":"Polish Read Speech Corpus for Speech Tools and Services","date":"2017-06-01","arxiv_id":"1706.00245","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-framework-for-the-automatic-inference-of","title":"A framework for the automatic inference of stochastic turn-taking styles","date":"2016-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"autoapprentissage-pour-le-regroupement-en","title":"Autoapprentissage pour le regroupement en locuteurs : premi\\`eres investigations (First investigations on self trained speaker diarization )","date":"2016-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-trax-a-bottom-to-the-top-approach-for","title":"Speech Trax: A Bottom to the Top Approach for Speaker Tracking and Indexing in an Archiving Context","date":"2016-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-speaker-diarization-based-on","title":"Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion","date":"2016-03-31","arxiv_id":"1603.09725","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-adaptation-of-splda","title":"Unsupervised Adaptation of SPLDA","date":"2015-11-20","arxiv_id":"1511.07421","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-effortless-way-to-create-large-scale","title":"An Effortless Way To Create Large-Scale Datasets For Famous Speakers","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"new-bilingual-speech-databases-for-audio","title":"New bilingual speech databases for audio diarization","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-etape-speech-processing-evaluation","title":"The ETAPE speech processing evaluation","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-modal-sensing-and-analysis-of-poster","title":"Multi-modal Sensing and Analysis of Poster Conversations: Toward Smart Posterboard","date":"2012-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"nouvelle-approche-pour-le-regroupement-des","title":"Nouvelle approche pour le regroupement des locuteurs dans des \\'emissions radiophoniques et t\\'el\\'evisuelles (New approach for speaker clustering of broadcast news) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"percol0-un-systeme-multimodal-de-detection-de","title":"Percol0 - un syst\\`eme multimodal de d\\'etection de personnes dans des documents vid\\'eo (Percol0 - A multimodal person detection system in video documents) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"segmentation-et-regroupement-en-locuteurs","title":"Segmentation et Regroupement en Locuteurs d'une collection de documents audio (Cross-show speaker diarization) [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"an-alternative-to-low-level-sychrony-based","title":"An Alternative to Low-level-Sychrony-Based Methods for Speech Detection","date":"2010-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-sticky-hdp-hmm-with-application-to-speaker","title":"A sticky HDP-HMM with application to speaker diarization","date":"2009-05-15","arxiv_id":"0905.2592","repositories_listed":0,"syntology":null}],"record_sha256":"85b00616a96dd36710086c92ea9ef20f4ce6140dfd86104b0b132ebbf21e3cef","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}