{"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-pretraining-transfers-well","title":"Unsupervised pretraining transfers well across languages","arxiv_id":"2002.02848","date":"2020-02-07","proceeding":null,"authors":["Morgane Rivière","Armand Joulin","Pierre-Emmanuel Mazaré","Emmanuel Dupoux"],"abstract":"Cross-lingual and multi-lingual training of Automatic Speech Recognition (ASR) has been extensively investigated in the supervised setting. This assumes the existence of a parallel corpus of speech and orthographic transcriptions. Recently, contrastive predictive coding (CPC) algorithms have been proposed to pretrain ASR systems with unlabelled data. In this work, we investigate whether unsupervised pretraining transfers well across languages. We show that a slight modification of the CPC pretraining extracts features that transfer well to other languages, being on par or even outperforming supervised pretraining. This shows the potential of unsupervised methods for languages with few linguistic resources.","url_abs":"https://arxiv.org/abs/2002.02848v1","url_pdf":"https://arxiv.org/pdf/2002.02848v1.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-pretraining-transfers-well","repo_url":"https://github.com/facebookresearch/CPC_audio","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"unsupervised-pretraining-transfers-well","repo_url":"https://github.com/chorowski-lab/CPC_audio","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"unsupervised-pretraining-transfers-well","repo_url":"https://github.com/chorowski-lab/hcpc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"contrastive-predictive-coding","method_name":"Contrastive Predictive Coding"},{"method_slug":"infonce","method_name":"InfoNCE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.02848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.02848"}},"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/chorowski-lab/CPC_audio","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/CPC_audio","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/chorowski-lab/hcpc","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"f5d2474d463058b0","entry":"parse_args","repo":"facebookresearch/CPC_audio","repo_kind":"official","path":"cpc/eval/linear_separability.py","file_url":"https://github.com/facebookresearch/CPC_audio/blob/HEAD/cpc/eval/linear_separability.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f5d2474d463058b0"}},{"code_sha256_prefix":"b4c2b5de7a1d9b50","entry":"reduce_sparse_data","repo":"facebookresearch/CPC_audio","repo_kind":"official","path":"cpc/eval/ABX.py","file_url":"https://github.com/facebookresearch/CPC_audio/blob/HEAD/cpc/eval/ABX.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b4c2b5de7a1d9b50"}},{"code_sha256_prefix":"9891603bc50b0600","entry":"parse_args","repo":"facebookresearch/CPC_audio","repo_kind":"official","path":"cpc/eval/ABX.py","file_url":"https://github.com/facebookresearch/CPC_audio/blob/HEAD/cpc/eval/ABX.py","link_basis":"first_harvest_node","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":"9891603bc50b0600"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}