{"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":"/method/xlsr","slug":"xlsr","name":"XLSR","full_name":"XLSR","full_name_withheld":false,"description_markdown":"**XLSR** is a multilingual speech recognition model built on wav2vec 2.0 which is trained by solving a contrastive task over masked latent speech representations and jointly learns a quantization of the latents shared across languages. The model is fine-tuned on labeled data and experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining. A shared quantization module over feature encoder representations produces multilingual quantized speech units whose embeddings are then used as targets for a [Transformer](https://paperswithcode.com/method/transformer) trained by contrastive learning. The model learns to share discrete tokens across languages, creating bridges across languages.","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":"https://arxiv.org/abs/2006.13979v2","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Audio","area_id":"audio","collection":"Speech Recognition","url":"/methods/category/speech-recognition","pwc_aliases":[]}],"n_papers_tagged":20,"archive_num_papers":null,"papers_newest_first":[{"paper":null,"slug":"2506-04652","title":"EMO-Debias: Benchmarking Gender Debiasing Techniques in Multi-Label Speech Emotion Recognition","date":"2025-06-05","arxiv_id":"2506.04652","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-asr-models-and-features-for","title":"Self-supervised ASR Models and Features For Dysarthric and Elderly Speech Recognition","date":"2024-07-03","arxiv_id":"2407.13782","n_code_links":0,"syntology":null},{"paper":null,"slug":"less-forgetting-for-better-generalization","title":"Less Forgetting for Better Generalization: Exploring Continual-learning Fine-tuning Methods for Speech Self-supervised Representations","date":"2024-06-30","arxiv_id":"2407.00756","n_code_links":0,"syntology":null},{"paper":null,"slug":"transcription-and-translation-of-videos-using","title":"Transcription and translation of videos using fine-tuned XLSR Wav2Vec2 on custom dataset and mBART","date":"2024-03-01","arxiv_id":"2403.00212","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-hindi-to-english-speech-conversion","title":"End to end Hindi to English speech conversion using Bark, mBART and a finetuned XLSR Wav2Vec2","date":"2024-01-11","arxiv_id":"2401.06183","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-supervised-adaptive-pre-training-of","title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","date":"2023-12-12","arxiv_id":"2312.07338","n_code_links":0,"syntology":null},{"paper":null,"slug":"multilingual-self-supervised-speech","title":"Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching","date":"2023-11-25","arxiv_id":"2311.15077","n_code_links":0,"syntology":null},{"paper":null,"slug":"modular-speech-to-text-translation-for-zero","title":"Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer","date":"2023-10-05","arxiv_id":"2310.03724","n_code_links":0,"syntology":null},{"paper":"/paper/zero-resource-code-switched-speech-benchmark","slug":"zero-resource-code-switched-speech-benchmark","title":"Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages","date":"2023-10-04","arxiv_id":"2310.03018","n_code_links":1,"syntology":null},{"paper":null,"slug":"indonesian-automatic-speech-recognition-with","title":"Indonesian Automatic Speech Recognition with XLSR-53","date":"2023-08-20","arxiv_id":"2308.11589","n_code_links":0,"syntology":null},{"paper":"/paper/allophant-cross-lingual-phoneme-recognition","slug":"allophant-cross-lingual-phoneme-recognition","title":"Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes","date":"2023-06-07","arxiv_id":"2306.04306","n_code_links":1,"syntology":null},{"paper":"/paper/improving-the-previous-state-of-the-art","slug":"improving-the-previous-state-of-the-art","title":"Improving the previous state-of-the-art Frisian ASR by fine-tuning XLS-R","date":"2023-03-31","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/improving-spoken-language-identification-with","slug":"improving-spoken-language-identification-with","title":"Improving Spoken Language Identification with Map-Mix","date":"2023-02-16","arxiv_id":"2302.08229","n_code_links":1,"syntology":null},{"paper":null,"slug":"improved-self-supervised-multilingual-speech","title":"Improved Self-Supervised Multilingual Speech Representation Learning Combined with Auxiliary Language Information","date":"2022-12-07","arxiv_id":"2212.03476","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-speech-recognition-of-low-resource","title":"Automatic Speech Recognition of Low-Resource Languages Based on Chukchi","date":"2022-10-11","arxiv_id":"2210.05726","n_code_links":0,"syntology":null},{"paper":null,"slug":"cross-lingual-self-supervised-speech","title":"Cross-lingual Self-Supervised Speech Representations for Improved Dysarthric Speech Recognition","date":"2022-04-04","arxiv_id":"2204.01670","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-adaptive-cross-lingual-speech","title":"Language Adaptive Cross-lingual Speech Representation Learning with Sparse Sharing Sub-networks","date":"2022-03-09","arxiv_id":"2203.04583","n_code_links":0,"syntology":null},{"paper":null,"slug":"joint-unsupervised-and-supervised-training","title":"Joint Unsupervised and Supervised Training for Multilingual ASR","date":"2021-11-15","arxiv_id":"2111.08137","n_code_links":0,"syntology":null},{"paper":null,"slug":"magic-dust-for-cross-lingual-adaptation-of","title":"Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0","date":"2021-10-07","arxiv_id":"2110.03560","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-cross-lingual-representation-3","slug":"unsupervised-cross-lingual-representation-3","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","date":"2020-06-24","arxiv_id":"2006.13979","n_code_links":8,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}}],"papers_shown":20,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":20,"with_a_code_link":4,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":20,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"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"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/xlsr/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/xlsr/papers/ran/1","json":"/method/xlsr/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/speech-recognition","name":"Speech Recognition","papers":15},{"task":"/task/speech-recognition-1","name":"speech-recognition","papers":14},{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":8},{"task":"/task/automatic-speech-recognition","name":"Automatic Speech Recognition (ASR)","papers":7},{"task":"/task/language-modeling","name":"Language Modeling","papers":4},{"task":"/task/language-modelling","name":"Language Modelling","papers":4},{"task":"/task/representation-learning","name":"Representation Learning","papers":3},{"task":"/task/translation","name":"Translation","papers":3},{"task":"/task/cross-lingual-transfer","name":"Cross-Lingual Transfer","papers":2},{"task":"/task/language-identification","name":"Language Identification","papers":2},{"task":"/task/speech-representation-learning","name":"Speech Representation Learning","papers":2},{"task":"/task/speech-to-text","name":"Speech-to-Text","papers":2},{"task":"/task/spoken-language-identification","name":"Spoken language identification","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/alzheimer-s-disease-detection","name":"Alzheimer's Disease Detection","papers":1},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/continual-learning","name":"Continual Learning","papers":1},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":1},{"task":"/task/dialect-identification","name":"Dialect Identification","papers":1}],"tasks_shown":20,"n_tasks":38,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":2},{"year":"2022","papers":4},{"year":"2023","papers":8},{"year":"2024","papers":4},{"year":"2025","papers":1}],"row_source":"embedded","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/xlsr"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=XLSR","read_at":"2026-10-05T01:04:01+00:00","query":"XLSR","kind":"method","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":null,"repositories":null,"retrieve_with":null,"name_competition":{"verdict":"none","may_be_wrong_sense":false,"bearers_found":0,"served":null,"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing in this corpus is named 'XLSR' -- no method node, no paper announcing it in its title, no expanded form declaring it as an acronym."},"name_competition_text":null,"near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"e06686d2ea79587d69e4c33ff33211666bf70991f17a4e08bd065331095119e9","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}