{"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/unsupervised-cross-lingual-representation-3","title":"Unsupervised Cross-lingual Representation Learning for Speech Recognition","arxiv_id":"2006.13979","date":"2020-06-24","proceeding":null,"authors":["Alexis Conneau","Alexei Baevski","Ronan Collobert","Abdel-rahman Mohamed","Michael Auli"],"abstract":"This paper presents XLSR which learns cross-lingual speech representations by pretraining a single model from the raw waveform of speech in multiple languages. We build 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 resulting model is fine-tuned on labeled data and experiments show that cross-lingual pretraining significantly outperforms monolingual pretraining. On the CommonVoice benchmark, XLSR shows a relative phoneme error rate reduction of 72% compared to the best known results. On BABEL, our approach improves word error rate by 16% relative compared to a comparable system. Our approach enables a single multilingual speech recognition model which is competitive to strong individual models. Analysis shows that the latent discrete speech representations are shared across languages with increased sharing for related languages. We hope to catalyze research in low-resource speech understanding by releasing XLSR-53, a large model pretrained in 53 languages.","url_abs":"https://arxiv.org/abs/2006.13979v2","url_pdf":"https://arxiv.org/pdf/2006.13979v2.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":"unsupervised-cross-lingual-representation-3","repo_url":"https://github.com/HLasse/wav2vec_finetune","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unsupervised-cross-lingual-representation-3","repo_url":"https://github.com/facebookresearch/fairseq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unsupervised-cross-lingual-representation-3","repo_url":"https://github.com/hltchkust/cantonese-asr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"unsupervised-cross-lingual-representation-3","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"unsupervised-cross-lingual-representation-3","repo_url":"https://github.com/marccanby/bidi_decoding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unsupervised-cross-lingual-representation-3","repo_url":"https://github.com/JoegameZhou/MindSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"unsupervised-cross-lingual-representation-3","repo_url":"https://github.com/MindCode-4/code-5/tree/main/xlm_roberta","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"unsupervised-cross-lingual-representation-3","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/1/xlm_roberta_xl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"xlsr","method_name":"XLSR"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.13979","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.13979"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/huggingface/transformers","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/fairseq","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/1/xlm_roberta_xl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-5/tree/main/xlm_roberta","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hltchkust/cantonese-asr","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marccanby/bidi_decoding","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HLasse/wav2vec_finetune","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/JoegameZhou/MindSpeech","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"1ac327c3640acdb7","entry":"create_trainer","repo":"HLasse/wav2vec_finetune","repo_kind":"listed","path":"train_baseline_models.py","file_url":"https://github.com/HLasse/wav2vec_finetune/blob/HEAD/train_baseline_models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ac327c3640acdb7"}},{"code_sha256_prefix":"2e846888099ed9e1","entry":"label2id","repo":"HLasse/wav2vec_finetune","repo_kind":"listed","path":"train_baseline_models.py","file_url":"https://github.com/HLasse/wav2vec_finetune/blob/HEAD/train_baseline_models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2e846888099ed9e1"}},{"code_sha256_prefix":"799709e0afdff68f","entry":"make_config","repo":"HLasse/wav2vec_finetune","repo_kind":"listed","path":"configs/make_binary_wav2vec_configs.py","file_url":"https://github.com/HLasse/wav2vec_finetune/blob/HEAD/configs/make_binary_wav2vec_configs.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"799709e0afdff68f"}},{"code_sha256_prefix":"61f33bdd096359a4","entry":"map_l2id","repo":"HLasse/wav2vec_finetune","repo_kind":"listed","path":"train_wav2vec_streaming.py","file_url":"https://github.com/HLasse/wav2vec_finetune/blob/HEAD/train_wav2vec_streaming.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"61f33bdd096359a4"}},{"code_sha256_prefix":"2c5f5e77e1131aae","entry":"preprocess_stacked_speech_files","repo":"HLasse/wav2vec_finetune","repo_kind":"listed","path":"train_wav2vec_streaming.py","file_url":"https://github.com/HLasse/wav2vec_finetune/blob/HEAD/train_wav2vec_streaming.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c5f5e77e1131aae"}},{"code_sha256_prefix":"9222522c819be1f6","entry":"stack_frames","repo":"HLasse/wav2vec_finetune","repo_kind":"listed","path":"src/make_windows.py","file_url":"https://github.com/HLasse/wav2vec_finetune/blob/HEAD/src/make_windows.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9222522c819be1f6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}