{"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/listen-and-translate-a-proof-of-concept-for","title":"Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation","arxiv_id":"1612.01744","date":"2016-12-06","proceeding":null,"authors":["Alexandre Berard","Olivier Pietquin","Christophe Servan","Laurent Besacier"],"abstract":"This paper proposes a first attempt to build an end-to-end speech-to-text\ntranslation system, which does not use source language transcription during\nlearning or decoding. We propose a model for direct speech-to-text translation,\nwhich gives promising results on a small French-English synthetic corpus.\nRelaxing the need for source language transcription would drastically change\nthe data collection methodology in speech translation, especially in\nunder-resourced scenarios. For instance, in the former project DARPA TRANSTAC\n(speech translation from spoken Arabic dialects), a large effort was devoted to\nthe collection of speech transcripts (and a prerequisite to obtain transcripts\nwas often a detailed transcription guide for languages with little standardized\nspelling). Now, if end-to-end approaches for speech-to-text translation are\nsuccessful, one might consider collecting data by asking bilingual speakers to\ndirectly utter speech in the source language from target language text\nutterances. Such an approach has the advantage to be applicable to any\nunwritten (source) language.","url_abs":"http://arxiv.org/abs/1612.01744v1","url_pdf":"http://arxiv.org/pdf/1612.01744v1.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":"listen-and-translate-a-proof-of-concept-for","repo_url":"https://github.com/eske/seq2seq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"speech-to-text","task_name":"Speech-to-Text"},{"task_slug":"speech-to-text-translation","task_name":"Speech-to-Text Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1612.01744","atlas_url":"https://app.syntology.ai/?focus=1612.01744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.01744"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/eske/seq2seq","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":15},"by_repo_kind":{"official":{"samples":15,"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":"1ff3291db854041a","entry":"apply_time_pooling","repo":"eske/seq2seq","repo_kind":"official","path":"translate/rnn.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/rnn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1ff3291db854041a"}},{"code_sha256_prefix":"68d6e78c95902674","entry":"auto_reuse","repo":"eske/seq2seq","repo_kind":"official","path":"translate/models.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"68d6e78c95902674"}},{"code_sha256_prefix":"1141b89c91c7f61c","entry":"get_best_score","repo":"eske/seq2seq","repo_kind":"official","path":"run-tests.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/run-tests.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1141b89c91c7f61c"}},{"code_sha256_prefix":"350b8500eef3645a","entry":"get_shape","repo":"eske/seq2seq","repo_kind":"official","path":"translate/beam_search.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/beam_search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"350b8500eef3645a"}},{"code_sha256_prefix":"06352e12d02c8738","entry":"get_state_size","repo":"eske/seq2seq","repo_kind":"official","path":"translate/rnn.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/rnn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"06352e12d02c8738"}},{"code_sha256_prefix":"2ac7677b1e6b3956","entry":"get_weights","repo":"eske/seq2seq","repo_kind":"official","path":"translate/beam_search.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/beam_search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ac7677b1e6b3956"}},{"code_sha256_prefix":"b64547c9e827d468","entry":"initialize_vocabulary","repo":"eske/seq2seq","repo_kind":"official","path":"translate/utils.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b64547c9e827d468"}},{"code_sha256_prefix":"d8042102ebe27b4c","entry":"levenshtein","repo":"eske/seq2seq","repo_kind":"official","path":"translate/evaluation.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d8042102ebe27b4c"}},{"code_sha256_prefix":"86988a69e7729805","entry":"resize_like","repo":"eske/seq2seq","repo_kind":"official","path":"translate/beam_search.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/beam_search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86988a69e7729805"}},{"code_sha256_prefix":"57a6b91d7cad71f0","entry":"reverse_edits","repo":"eske/seq2seq","repo_kind":"official","path":"translate/utils.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"57a6b91d7cad71f0"}},{"code_sha256_prefix":"c2cc86fca14350af","entry":"score_function_decorator","repo":"eske/seq2seq","repo_kind":"official","path":"translate/evaluation.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c2cc86fca14350af"}},{"code_sha256_prefix":"fb51636d55302b3b","entry":"sentence_bleu","repo":"eske/seq2seq","repo_kind":"official","path":"translate/evaluation.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb51636d55302b3b"}},{"code_sha256_prefix":"4f84c74cf4c69c83","entry":"sentence_to_token_ids","repo":"eske/seq2seq","repo_kind":"official","path":"translate/utils.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4f84c74cf4c69c83"}},{"code_sha256_prefix":"94dc1f1512737035","entry":"sort_key","repo":"eske/seq2seq","repo_kind":"official","path":"config/AMU/avg.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/config/AMU/avg.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"94dc1f1512737035"}},{"code_sha256_prefix":"92c33312592e9111","entry":"stack_bidirectional_dynamic_rnn","repo":"eske/seq2seq","repo_kind":"official","path":"translate/rnn.py","file_url":"https://github.com/eske/seq2seq/blob/HEAD/translate/rnn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"92c33312592e9111"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}