{"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-identification/papers/3","list_of":"/task/speaker-identification","task":"Speaker Identification","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":3,"pages_in_order":3,"rows_per_page":100,"rows":[201,248],"of":248,"counts":{"archive_papers_tagged":248,"with_a_code_link":74,"where_syntology_ran_a_sample":15,"not_listed_spam_title":0,"listed":248,"listed_where_code_ran":15,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":11,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":11,"listed_every_run_a_failure_of_syntologys_instrument":4,"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-identification","prev":"/task/speaker-identification/papers/2","next":null,"papers":[{"url":null,"slug":"adaptive-blind-audio-source-extraction","title":"Adaptive blind audio source extraction supervised by dominant speaker identification using x-vectors","date":"2019-10-25","arxiv_id":"1910.11824","repositories_listed":0,"syntology":null},{"url":null,"slug":"h-vectors-utterance-level-speaker-embedding","title":"H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model","date":"2019-10-17","arxiv_id":"1910.07900","repositories_listed":0,"syntology":null},{"url":null,"slug":"emirati-accented-speaker-identification-in","title":"Emirati-Accented Speaker Identification in Stressful Talking Conditions","date":"2019-09-28","arxiv_id":"1909.13070","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-robustness-in-speaker","title":"Improving Noise Robustness In Speaker Identification Using A Two-Stage Attention Model","date":"2019-09-24","arxiv_id":"1909.11200","repositories_listed":0,"syntology":null},{"url":null,"slug":"cosine-similarity-based-adversarial-process","title":"Cosine similarity-based adversarial process","date":"2019-07-01","arxiv_id":"1907.00542","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-speaker-diarization-of-radio","title":"Large-Scale Speaker Diarization of Radio Broadcast Archives","date":"2019-06-19","arxiv_id":"1906.07955","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-user-study-to-compare-two-conversational","title":"A user study to compare two conversational assistants designed for people with hearing impairments","date":"2019-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"190502525","title":"Many-to-Many Voice Conversion with Out-of-Dataset Speaker Support","date":"2019-04-30","arxiv_id":"1905.02525","repositories_listed":0,"syntology":null},{"url":null,"slug":"experiments-on-open-set-speaker","title":"Experiments on Open-Set Speaker Identification with Discriminatively Trained Neural Networks","date":"2019-04-02","arxiv_id":"1904.01269","repositories_listed":0,"syntology":null},{"url":null,"slug":"advanced-rich-transcription-system-for","title":"Advanced Rich Transcription System for Estonian Speech","date":"2019-01-11","arxiv_id":"1901.03601","repositories_listed":0,"syntology":null},{"url":null,"slug":"histogram-transform-based-speaker","title":"Histogram Transform-based Speaker Identification","date":"2018-08-02","arxiv_id":"1808.00959","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":"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":"evaluation-of-automatic-formant-trackers","title":"Evaluation of Automatic Formant Trackers","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-speakers-and-addressees-in","title":"Identifying Speakers and Addressees in Dialogues Extracted from Literary Fiction","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":"vast-a-corpus-of-video-annotation-for-speech","title":"VAST: A Corpus of Video Annotation for Speech Technologies","date":"2018-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"seeing-voices-and-hearing-faces-cross-modal","title":"Seeing Voices and Hearing Faces: Cross-modal biometric matching","date":"2018-04-01","arxiv_id":"1804.00326","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-predictive-coding-using-convolutional","title":"Neural Predictive Coding using Convolutional Neural Networks towards Unsupervised Learning of Speaker Characteristics","date":"2018-02-22","arxiv_id":"1802.07860","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-benedict-cumberbatch-to-sherlock-holmes","title":"From Benedict Cumberbatch to Sherlock Holmes: Character Identification in TV series without a Script","date":"2018-01-31","arxiv_id":"1801.10442","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-identification-from-the-sound-of-the","title":"Speaker identification from the sound of the human breath","date":"2017-12-01","arxiv_id":"1712.00171","repositories_listed":0,"syntology":null},{"url":null,"slug":"ao14e12eoc-aa1ii-cc2iaaa-eaei14aa-a1c-two","title":"基於聽覺感知模型之類神經網路及其在語者識別上之應用 (Two-stage Attentional Auditory Model Inspired Neural Network and Its Application to Speaker Identification) [In Chinese]","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"identifying-speakers-and-listeners-of-quoted","title":"Identifying Speakers and Listeners of Quoted Speech in Literary Works","date":"2017-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/story-comprehension-for-predicting-what","slug":"story-comprehension-for-predicting-what","title":"Story Comprehension for Predicting What Happens Next","date":"2017-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-multiple-features-and-modeling","title":"Comparison of Multiple Features and Modeling Methods for Text-dependent Speaker Verification","date":"2017-07-14","arxiv_id":"1707.04373","repositories_listed":0,"syntology":null},{"url":null,"slug":"face-recognition-with-machine-learning-in","title":"Face Recognition with Machine Learning in OpenCV_ Fusion of the results with the Localization Data of an Acoustic Camera for Speaker Identification","date":"2017-07-04","arxiv_id":"1707.00835","repositories_listed":0,"syntology":null},{"url":null,"slug":"text-based-speaker-identification-on","title":"Text-based Speaker Identification on Multiparty Dialogues Using Multi-document Convolutional Neural Networks","date":"2017-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-identification-in-each-of-the-neutral","title":"Speaker Identification in each of the Neutral and Shouted Talking Environments based on Gender-Dependent Approach Using SPHMMs","date":"2017-06-29","arxiv_id":"1706.09767","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-musical-emotion-be-quantified-with-neural","title":"Can Musical Emotion Be Quantified With Neural Jitter Or Shimmer? A Novel EEG Based Study With Hindustani Classical Music","date":"2017-04-29","arxiv_id":"1705.03543","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-unsupervised-speaker-clustering-technique","title":"An Unsupervised Speaker Clustering Technique based on SOM and I-vectors for Speech Recognition Systems","date":"2017-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"discrimination-between-similar-languages","title":"Discrimination between Similar Languages, Varieties and Dialects using CNN- and LSTM-based Deep Neural Networks","date":"2016-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"monaural-multi-talker-speech-recognition","title":"Monaural Multi-Talker Speech Recognition using Factorial Speech Processing Models","date":"2016-10-05","arxiv_id":"1610.01367","repositories_listed":0,"syntology":null},{"url":null,"slug":"curie-a-method-for-protecting-svm-classifier","title":"Curie: A method for protecting SVM Classifier from Poisoning Attack","date":"2016-06-05","arxiv_id":"1606.01584","repositories_listed":0,"syntology":null},{"url":null,"slug":"look-listen-and-learn-a-multimodal-lstm-for","title":"Look, Listen and Learn - A Multimodal LSTM for Speaker Identification","date":"2016-02-13","arxiv_id":"1602.04364","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-minimum-divergence-approach-to-robust","title":"A Novel Minimum Divergence Approach to Robust Speaker Identification","date":"2015-12-16","arxiv_id":"1512.05073","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-identification-from-youtube-obtained","title":"Speaker Identification From Youtube Obtained Data","date":"2014-11-11","arxiv_id":"1411.2795","repositories_listed":0,"syntology":null},{"url":null,"slug":"invited-talk-ibm-cognitive-computing-an-nlp","title":"Invited Talk: IBM Cognitive Computing - An NLP Renaissance!","date":"2014-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-representation-based-speaker","title":"基於稀疏表示之語者識別 (Sparse Representation Based Speaker Identification) [In Chinese]","date":"2014-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multi-level-data-fusion-approach-for","title":"A Multi Level Data Fusion Approach for Speaker Identification on Telephone Speech","date":"2014-06-27","arxiv_id":"1407.0380","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-use-of-different-feature-extraction","title":"On the Use of Different Feature Extraction Methods for Linear and Non Linear kernels","date":"2014-06-27","arxiv_id":"1406.7314","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-gender-and-speaker-adaptive","title":"Comparison of Gender- and Speaker-adaptive Emotion Recognition","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-dirha-simulated-corpus","title":"The DIRHA simulated corpus","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-rats-collection-supporting-hlt-research","title":"The RATS Collection: Supporting HLT Research with Degraded Audio Data","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-model-for-quotation-attribution-and","title":"A Joint Model for Quotation Attribution and Coreference Resolution","date":"2014-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"from-speaker-identification-to-affective","title":"From Speaker Identification to Affective Analysis: A Multi-Step System for Analyzing Children's Stories","date":"2014-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"identification-of-speakers-in-novels","title":"Identification of Speakers in Novels","date":"2013-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"mkpls-manifold-kernel-partial-least-squares","title":"MKPLS: Manifold Kernel Partial Least Squares for Lipreading and Speaker Identification","date":"2013-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"lidentification-du-locuteur-20-ans-de","title":"L'identification du locuteur : 20 ans de t\\'emoignage dans les cours de Justice. Le cas du LIPSADON \\textless\\textless laboratoire ind\\'ependant de police scientifique \\textgreater\\textgreater (Forensic speaker identification: 20 years of scientific testimonies in courts of Justice. The case of LIPSADON ``forensics independent laboratory'') [in French]","date":"2012-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"record_sha256":"2c4658367b10fc208cefb94d73c4bda29bc1bfcb1b5a31e671aa7a0596b60bf2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}