{"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/speech-to-text-translation","name":"Speech-to-Text Translation","slug":"speech-to-text-translation","description_markdown":"Translate audio signals of speech in one language into text in a foreign language, either in an end-to-end or cascade manner.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":146,"papers_with_code":64,"benchmarks":11,"benchmark_tables_in_archive":11,"benchmark_tables_shown":11,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/speech-to-text-translation-on-must-c-en-de","slug":"speech-to-text-translation-on-must-c-en-de","dataset":"MuST-C EN->DE","dataset_url":"/dataset/must-c","rows_in_archive":8,"metrics":["Case-sensitive sacreBLEU"],"first_row_in_archive_order":{"model":"Task Modulation + Multitask Learning(ASR/MT) + Data Augmentation","paper_title":"TASK AWARE MULTI-TASK LEARNING FOR SPEECH TO TEXT TASKS","paper_url":"/paper/task-aware-multi-task-learning-for-speech-to","paper_date":"2021-06-10","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/speech-to-text-translation-on-must-c-en-es","slug":"speech-to-text-translation-on-must-c-en-es","dataset":"MuST-C EN->ES","dataset_url":null,"rows_in_archive":5,"metrics":["Case-sensitive sacreBLEU"],"first_row_in_archive_order":{"model":"Transformer with Adapters","paper_title":"Lightweight Adapter Tuning for Multilingual Speech Translation","paper_url":"/paper/lightweight-adapter-tuning-for-multilingual","paper_date":"2021-06-02","arxiv_id":"2106.01463","code_links":[{"title":"formiel/fairseq","url":"https://github.com/formiel/fairseq"},{"title":"formiel/fairseq","url":"https://github.com/formiel/fairseq/blob/master/examples/speech_to_text/docs/adapters.md"}],"syntology":null}},{"leaderboard":"/sota/speech-to-text-translation-on-must-c-en-fr","slug":"speech-to-text-translation-on-must-c-en-fr","dataset":"MuST-C EN->FR","dataset_url":null,"rows_in_archive":3,"metrics":["Case-sensitive sacreBLEU"],"first_row_in_archive_order":{"model":"Dual-decoder Transformer","paper_title":"Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation","paper_url":"/paper/dual-decoder-transformer-for-joint-automatic","paper_date":"2020-11-02","arxiv_id":"2011.00747","code_links":[{"title":"formiel/speech-translation","url":"https://github.com/formiel/speech-translation"}],"syntology":null}},{"leaderboard":"/sota/speech-to-text-translation-on-covost-2-eng-x","slug":"speech-to-text-translation-on-covost-2-eng-x","dataset":"CoVoST 2 eng-X","dataset_url":null,"rows_in_archive":2,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"SeamlessM4T Large","paper_title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","paper_url":"/paper/seamlessm4t-massively-multilingual-multimodal","paper_date":"2023-08-22","arxiv_id":"2308.11596","code_links":[{"title":"facebookresearch/seamless_communication","url":"https://github.com/facebookresearch/seamless_communication"},{"title":"facebookresearch/sonar","url":"https://github.com/facebookresearch/sonar"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/seamless_m4t"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/seamless_m4t"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seamlessm4t-massively-multilingual-multimodal#ran","syntology_url":"https://syntology.ai/paper/2308.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11596"}},"official":{"repos":["facebookresearch/seamless_communication"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/speech-to-text-translation-on-covost-2-x-eng","slug":"speech-to-text-translation-on-covost-2-x-eng","dataset":"CoVoST 2 X-eng","dataset_url":null,"rows_in_archive":2,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"SeamlessM4T Large","paper_title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","paper_url":"/paper/seamlessm4t-massively-multilingual-multimodal","paper_date":"2023-08-22","arxiv_id":"2308.11596","code_links":[{"title":"facebookresearch/seamless_communication","url":"https://github.com/facebookresearch/seamless_communication"},{"title":"facebookresearch/sonar","url":"https://github.com/facebookresearch/sonar"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/seamless_m4t"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/seamless_m4t"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seamlessm4t-massively-multilingual-multimodal#ran","syntology_url":"https://syntology.ai/paper/2308.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11596"}},"official":{"repos":["facebookresearch/seamless_communication"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/speech-to-text-translation-on-fleurs-eng-x","slug":"speech-to-text-translation-on-fleurs-eng-x","dataset":"FLEURS eng-X","dataset_url":null,"rows_in_archive":2,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"SeamlessM4T Large","paper_title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","paper_url":"/paper/seamlessm4t-massively-multilingual-multimodal","paper_date":"2023-08-22","arxiv_id":"2308.11596","code_links":[{"title":"facebookresearch/seamless_communication","url":"https://github.com/facebookresearch/seamless_communication"},{"title":"facebookresearch/sonar","url":"https://github.com/facebookresearch/sonar"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/seamless_m4t"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/seamless_m4t"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seamlessm4t-massively-multilingual-multimodal#ran","syntology_url":"https://syntology.ai/paper/2308.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11596"}},"official":{"repos":["facebookresearch/seamless_communication"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/speech-to-text-translation-on-fleurs-x-eng","slug":"speech-to-text-translation-on-fleurs-x-eng","dataset":"FLEURS X-eng","dataset_url":null,"rows_in_archive":2,"metrics":["BLEU"],"first_row_in_archive_order":{"model":"SeamlessM4T Large","paper_title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","paper_url":"/paper/seamlessm4t-massively-multilingual-multimodal","paper_date":"2023-08-22","arxiv_id":"2308.11596","code_links":[{"title":"facebookresearch/seamless_communication","url":"https://github.com/facebookresearch/seamless_communication"},{"title":"facebookresearch/sonar","url":"https://github.com/facebookresearch/sonar"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/seamless_m4t"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/seamless_m4t"}],"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seamlessm4t-massively-multilingual-multimodal#ran","syntology_url":"https://syntology.ai/paper/2308.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11596"}},"official":{"repos":["facebookresearch/seamless_communication"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/speech-to-text-translation-on-libri-trans","slug":"speech-to-text-translation-on-libri-trans","dataset":"libri-trans","dataset_url":null,"rows_in_archive":2,"metrics":["Case-insensitive sacreBLEU","Case-insensitive tokenized BLEU","Case-sensitive sacreBLEU","Case-sensitive tokenized BLEU"],"first_row_in_archive_order":{"model":"Transformer + ASR Pretrain + SpecAug","paper_title":"NeurST: Neural Speech Translation Toolkit","paper_url":"/paper/neurst-neural-speech-translation-toolkit","paper_date":"2020-12-18","arxiv_id":"2012.10018","code_links":[{"title":"bytedance/neurst","url":"https://github.com/bytedance/neurst"}],"syntology":null}},{"leaderboard":"/sota/speech-to-text-translation-on-medibeng","slug":"speech-to-text-translation-on-medibeng","dataset":"MediBeng","dataset_url":"/dataset/medibeng","rows_in_archive":2,"metrics":["Bleu"],"first_row_in_archive_order":{"model":"MediBeng Whisper Tiny","paper_title":"MEDIBENG WHISPER TINY: A FINE-TUNED CODE-SWITCHED BENGALI-ENGLISH TRANSLATOR FOR CLINICAL APPLICATIONS","paper_url":"/paper/medibeng-whisper-tiny-a-fine-tuned-code","paper_date":"2025-04-25","arxiv_id":null,"code_links":[{"title":"pr0mila/MediBeng-Whisper-Tiny","url":"https://github.com/pr0mila/MediBeng-Whisper-Tiny"}],"syntology":null}},{"leaderboard":"/sota/speech-to-text-translation-on-must-c-1","slug":"speech-to-text-translation-on-must-c-1","dataset":"MuST-C","dataset_url":"/dataset/must-c","rows_in_archive":2,"metrics":["SacreBLEU"],"first_row_in_archive_order":{"model":"Transformer with Adapters","paper_title":"Lightweight Adapter Tuning for Multilingual Speech Translation","paper_url":"/paper/lightweight-adapter-tuning-for-multilingual","paper_date":"2021-06-02","arxiv_id":"2106.01463","code_links":[{"title":"formiel/fairseq","url":"https://github.com/formiel/fairseq"},{"title":"formiel/fairseq","url":"https://github.com/formiel/fairseq/blob/master/examples/speech_to_text/docs/adapters.md"}],"syntology":null}},{"leaderboard":"/sota/speech-to-text-translation-on-must-c-en-nl","slug":"speech-to-text-translation-on-must-c-en-nl","dataset":"MuST-C EN->NL","dataset_url":null,"rows_in_archive":1,"metrics":["Case-sensitive sacreBLEU"],"first_row_in_archive_order":{"model":"Speechformer","paper_title":"Speechformer: Reducing Information Loss in Direct Speech Translation","paper_url":"/paper/speechformer-reducing-information-loss-in","paper_date":"2021-09-09","arxiv_id":"2109.04574","code_links":[{"title":"sarapapi/fbk-fairseq","url":"https://github.com/sarapapi/fbk-fairseq"}],"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/speechformer-reducing-information-loss-in#ran","syntology_url":"https://syntology.ai/paper/2109.04574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04574"}},"official":{"repos":["sarapapi/fbk-fairseq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}}}],"datasets":[{"url":"/dataset/must-c","name":"MuST-C","full_name":"","num_papers_in_archive":216},{"url":"/dataset/covost","name":"CoVoST","full_name":"","num_papers_in_archive":34},{"url":"/dataset/kosp2e","name":"Kosp2e","full_name":"","num_papers_in_archive":4},{"url":"/dataset/medibeng","name":"MediBeng","full_name":"Synthetic Code-Switched Bengali-English Speech Conversations for Healthcare Applications","num_papers_in_archive":1}],"subtasks":[{"url":"/task/simultaneous-speech-to-text-translation","name":"Simultaneous Speech-to-Text Translation"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":2,"rows_per_page":100,"shown":100,"of":146,"of_with_code":64,"tagged_in_all":146,"counts":{"archive_papers_tagged":146,"with_a_code_link":64,"where_syntology_ran_a_sample":15,"not_listed_spam_title":0,"listed":146,"listed_where_code_ran":15,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":8,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":8,"listed_every_run_a_failure_of_syntologys_instrument":7,"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"},"items":[{"url":"/paper/fairseq-s2t-fast-speech-to-text-modeling-with","slug":"fairseq-s2t-fast-speech-to-text-modeling-with","title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","date":"2020-10-11","arxiv_id":"2010.05171","repositories_listed":5,"syntology":null},{"url":"/paper/seamlessm4t-massively-multilingual-multimodal","slug":"seamlessm4t-massively-multilingual-multimodal","title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","date":"2023-08-22","arxiv_id":"2308.11596","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/seamlessm4t-massively-multilingual-multimodal#ran","syntology_url":"https://syntology.ai/paper/2308.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11596"}},"official":{"repos":["facebookresearch/seamless_communication"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/lauragpt-listen-attend-understand-and","slug":"lauragpt-listen-attend-understand-and","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","date":"2023-10-07","arxiv_id":"2310.04673","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_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) · 0 unverified","sample_list":"/paper/lauragpt-listen-attend-understand-and#ran","syntology_url":"https://syntology.ai/paper/2310.04673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04673"}},"official":null}},{"url":"/paper/paddlespeech-an-easy-to-use-all-in-one-speech-1","slug":"paddlespeech-an-easy-to-use-all-in-one-speech-1","title":"PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit","date":"2022-05-20","arxiv_id":"2205.12007","repositories_listed":2,"syntology":null},{"url":"/paper/a-3-t-alignment-aware-acoustic-and-text","slug":"a-3-t-alignment-aware-acoustic-and-text","title":"A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing","date":"2022-03-18","arxiv_id":"2203.09690","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/a-3-t-alignment-aware-acoustic-and-text#ran","syntology_url":"https://syntology.ai/paper/2203.09690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09690"}},"official":null}},{"url":"/paper/shas-approaching-optimal-segmentation-for-end","slug":"shas-approaching-optimal-segmentation-for-end","title":"SHAS: Approaching optimal Segmentation for End-to-End Speech Translation","date":"2022-02-09","arxiv_id":"2202.04774","repositories_listed":2,"syntology":null},{"url":"/paper/lightweight-adapter-tuning-for-multilingual","slug":"lightweight-adapter-tuning-for-multilingual","title":"Lightweight Adapter Tuning for Multilingual Speech Translation","date":"2021-06-02","arxiv_id":"2106.01463","repositories_listed":2,"syntology":null},{"url":"/paper/learning-shared-semantic-space-for-speech-to","slug":"learning-shared-semantic-space-for-speech-to","title":"Learning Shared Semantic Space for Speech-to-Text Translation","date":"2021-05-07","arxiv_id":"2105.03095","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-shared-semantic-space-for-speech-to#ran","syntology_url":"https://syntology.ai/paper/2105.03095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03095"}},"official":{"repos":["Glaciohound/Chimera-SLT","Glaciohound/Chimera-ST"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/covost-2-a-massively-multilingual-speech-to","slug":"covost-2-a-massively-multilingual-speech-to","title":"CoVoST 2 and Massively Multilingual Speech-to-Text Translation","date":"2020-07-20","arxiv_id":"2007.10310","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/covost-2-a-massively-multilingual-speech-to#ran","syntology_url":"https://syntology.ai/paper/2007.10310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10310"}},"official":{"repos":["facebookresearch/covost"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/beavertalk-oregon-state-university-s-iwslt","slug":"beavertalk-oregon-state-university-s-iwslt","title":"BeaverTalk: Oregon State University's IWSLT 2025 Simultaneous Speech Translation System","date":"2025-05-29","arxiv_id":"2505.24016","repositories_listed":1,"syntology":null},{"url":"/paper/audio-jailbreak-attacks-exposing","slug":"audio-jailbreak-attacks-exposing","title":"Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework","date":"2025-05-24","arxiv_id":"2505.18864","repositories_listed":1,"syntology":null},{"url":"/paper/medibeng-whisper-tiny-a-fine-tuned-code","slug":"medibeng-whisper-tiny-a-fine-tuned-code","title":"MEDIBENG WHISPER TINY: A FINE-TUNED CODE-SWITCHED BENGALI-ENGLISH TRANSLATOR FOR CLINICAL APPLICATIONS","date":"2025-04-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/sparqle-speech-queries-to-text-translation","slug":"sparqle-speech-queries-to-text-translation","title":"SparQLe: Speech Queries to Text Translation Through LLMs","date":"2025-02-13","arxiv_id":"2502.09284","repositories_listed":1,"syntology":null},{"url":"/paper/fleurs-slu-a-massively-multilingual-benchmark","slug":"fleurs-slu-a-massively-multilingual-benchmark","title":"Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding","date":"2025-01-10","arxiv_id":"2501.06117","repositories_listed":1,"syntology":null},{"url":"/paper/llast-improved-end-to-end-speech-translation","slug":"llast-improved-end-to-end-speech-translation","title":"LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models","date":"2024-07-22","arxiv_id":"2407.15415","repositories_listed":1,"syntology":null},{"url":"/paper/covoswitch-machine-translation-of-synthetic","slug":"covoswitch-machine-translation-of-synthetic","title":"CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units","date":"2024-07-19","arxiv_id":"2407.14295","repositories_listed":1,"syntology":null},{"url":"/paper/listen-and-speak-fairly-a-study-on-semantic","slug":"listen-and-speak-fairly-a-study-on-semantic","title":"Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models","date":"2024-07-09","arxiv_id":"2407.06957","repositories_listed":1,"syntology":null},{"url":"/paper/voices-unheard-nlp-resources-and-models-for","slug":"voices-unheard-nlp-resources-and-models-for","title":"Voices Unheard: NLP Resources and Models for Yorùbá Regional Dialects","date":"2024-06-27","arxiv_id":"2406.19564","repositories_listed":1,"syntology":null},{"url":"/paper/arzen-llm-code-switched-egyptian-arabic","slug":"arzen-llm-code-switched-egyptian-arabic","title":"ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs","date":"2024-06-26","arxiv_id":"2406.18120","repositories_listed":1,"syntology":null},{"url":"/paper/simulseamless-fbk-at-iwslt-2024-simultaneous","slug":"simulseamless-fbk-at-iwslt-2024-simultaneous","title":"SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation","date":"2024-06-20","arxiv_id":"2406.14177","repositories_listed":1,"syntology":null},{"url":"/paper/streamatt-direct-streaming-speech-to-text","slug":"streamatt-direct-streaming-speech-to-text","title":"StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection","date":"2024-06-10","arxiv_id":"2406.06097","repositories_listed":1,"syntology":null},{"url":"/paper/streamspeech-simultaneous-speech-to-speech","slug":"streamspeech-simultaneous-speech-to-speech","title":"StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning","date":"2024-06-05","arxiv_id":"2406.03049","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/streamspeech-simultaneous-speech-to-speech#ran","syntology_url":"https://syntology.ai/paper/2406.03049","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03049"}},"official":{"repos":["ictnlp/streamspeech"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/leapformer-enabling-linear-transformers-for","slug":"leapformer-enabling-linear-transformers-for","title":"LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions","date":"2024-05-18","arxiv_id":"2405.13046","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/leapformer-enabling-linear-transformers-for#ran","syntology_url":"https://syntology.ai/paper/2405.13046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13046"}},"official":{"repos":["osu-starlab/leapformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/pushing-the-limits-of-zero-shot-end-to-end","slug":"pushing-the-limits-of-zero-shot-end-to-end","title":"Pushing the Limits of Zero-shot End-to-End Speech Translation","date":"2024-02-16","arxiv_id":"2402.10422","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-zero-shot-generalizability-on","slug":"investigating-zero-shot-generalizability-on","title":"Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision","date":"2023-12-30","arxiv_id":"2401.00273","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-single-channel-speaker-turn-aware","slug":"end-to-end-single-channel-speaker-turn-aware","title":"End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation","date":"2023-11-01","arxiv_id":"2311.00697","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-consistency","slug":"an-empirical-study-of-consistency","title":"An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation","date":"2023-08-28","arxiv_id":"2308.14482","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-level-multimodal-and-language","slug":"sentence-level-multimodal-and-language","title":"SONAR: Sentence-Level Multimodal and Language-Agnostic Representations","date":"2023-08-22","arxiv_id":"2308.11466","repositories_listed":1,"syntology":null},{"url":"/paper/comsl-a-composite-speech-language-model-for-1","slug":"comsl-a-composite-speech-language-model-for-1","title":"ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation","date":"2023-05-24","arxiv_id":"2305.14838","repositories_listed":1,"syntology":null},{"url":"/paper/dub-discrete-unit-back-translation-for-speech","slug":"dub-discrete-unit-back-translation-for-speech","title":"DUB: Discrete Unit Back-translation for Speech Translation","date":"2023-05-19","arxiv_id":"2305.11411","repositories_listed":1,"syntology":null},{"url":"/paper/back-translation-for-speech-to-text","slug":"back-translation-for-speech-to-text","title":"Back Translation for Speech-to-text Translation Without Transcripts","date":"2023-05-15","arxiv_id":"2305.08709","repositories_listed":1,"syntology":null},{"url":"/paper/espnet-st-v2-multipurpose-spoken-language","slug":"espnet-st-v2-multipurpose-spoken-language","title":"ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit","date":"2023-04-10","arxiv_id":"2304.04596","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/espnet-st-v2-multipurpose-spoken-language#ran","syntology_url":"https://syntology.ai/paper/2304.04596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04596"}},"official":{"repos":["espnet/espnet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/muavic-a-multilingual-audio-visual-corpus-for","slug":"muavic-a-multilingual-audio-visual-corpus-for","title":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation","date":"2023-03-01","arxiv_id":"2303.00628","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-for-speech-translation-ctc-meets","slug":"pre-training-for-speech-translation-ctc-meets","title":"Pre-training for Speech Translation: CTC Meets Optimal Transport","date":"2023-01-27","arxiv_id":"2301.11716","repositories_listed":1,"syntology":null},{"url":"/paper/waco-word-aligned-contrastive-learning-for","slug":"waco-word-aligned-contrastive-learning-for","title":"WACO: Word-Aligned Contrastive Learning for Speech Translation","date":"2022-12-19","arxiv_id":"2212.09359","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-speech-translation-with-dynamic","slug":"efficient-speech-translation-with-dynamic","title":"Efficient Speech Translation with Dynamic Latent Perceivers","date":"2022-10-28","arxiv_id":"2210.16264","repositories_listed":1,"syntology":null},{"url":"/paper/don-t-discard-fixed-window-audio-segmentation","slug":"don-t-discard-fixed-window-audio-segmentation","title":"Don't Discard Fixed-Window Audio Segmentation in Speech-to-Text Translation","date":"2022-10-24","arxiv_id":"2210.13363","repositories_listed":1,"syntology":null},{"url":"/paper/m-adapter-modality-adaptation-for-end-to-end","slug":"m-adapter-modality-adaptation-for-end-to-end","title":"M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation","date":"2022-07-03","arxiv_id":"2207.00952","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-end-to-end-speech-to-text","slug":"revisiting-end-to-end-speech-to-text","title":"Revisiting End-to-End Speech-to-Text Translation From Scratch","date":"2022-06-09","arxiv_id":"2206.04571","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/revisiting-end-to-end-speech-to-text#ran","syntology_url":"https://syntology.ai/paper/2206.04571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04571"}},"official":{"repos":["bzhangGo/zero"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/cross-modal-contrastive-learning-for-speech-1","slug":"cross-modal-contrastive-learning-for-speech-1","title":"Cross-modal Contrastive Learning for Speech Translation","date":"2022-05-05","arxiv_id":"2205.02444","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cross-modal-contrastive-learning-for-speech-1#ran","syntology_url":"https://syntology.ai/paper/2205.02444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.02444"}},"official":{"repos":["reneeye/const"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/wav2seq-pre-training-speech-to-text-encoder","slug":"wav2seq-pre-training-speech-to-text-encoder","title":"Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","date":"2022-05-02","arxiv_id":"2205.01086","repositories_listed":1,"syntology":null},{"url":"/paper/libris2s-a-german-english-speech-to-speech","slug":"libris2s-a-german-english-speech-to-speech","title":"LibriS2S: A German-English Speech-to-Speech Translation Corpus","date":"2022-04-22","arxiv_id":"2204.10593","repositories_listed":1,"syntology":null},{"url":"/paper/stemm-self-learning-with-speech-text-manifold","slug":"stemm-self-learning-with-speech-text-manifold","title":"STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation","date":"2022-03-20","arxiv_id":"2203.10426","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/stemm-self-learning-with-speech-text-manifold#ran","syntology_url":"https://syntology.ai/paper/2203.10426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10426"}},"official":{"repos":["ictnlp/stemm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/cvss-corpus-and-massively-multilingual-speech","slug":"cvss-corpus-and-massively-multilingual-speech","title":"CVSS Corpus and Massively Multilingual Speech-to-Speech Translation","date":"2022-01-11","arxiv_id":"2201.03713","repositories_listed":1,"syntology":null},{"url":"/paper/regularizing-end-to-end-speech-translation","slug":"regularizing-end-to-end-speech-translation","title":"Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement","date":"2021-12-21","arxiv_id":"2112.10991","repositories_listed":1,"syntology":null},{"url":"/paper/unist-unified-end-to-end-model-for-streaming","slug":"unist-unified-end-to-end-model-for-streaming","title":"Learning When to Translate for Streaming Speech","date":"2021-09-15","arxiv_id":"2109.07368","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unist-unified-end-to-end-model-for-streaming#ran","syntology_url":"https://syntology.ai/paper/2109.07368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.07368"}},"official":{"repos":["dqqcasia/mosst"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/speechformer-reducing-information-loss-in","slug":"speechformer-reducing-information-loss-in","title":"Speechformer: Reducing Information Loss in Direct Speech Translation","date":"2021-09-09","arxiv_id":"2109.04574","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/speechformer-reducing-information-loss-in#ran","syntology_url":"https://syntology.ai/paper/2109.04574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04574"}},"official":{"repos":["sarapapi/fbk-fairseq"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/infusing-future-information-into-monotonic","slug":"infusing-future-information-into-monotonic","title":"Infusing Future Information into Monotonic Attention Through Language Models","date":"2021-09-07","arxiv_id":"2109.03121","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-the-reordering-capability-in","slug":"investigating-the-reordering-capability-in","title":"Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation","date":"2021-05-11","arxiv_id":"2105.04840","repositories_listed":1,"syntology":null},{"url":"/paper/upc-s-speech-translation-system-for-iwslt","slug":"upc-s-speech-translation-system-for-iwslt","title":"End-to-End Speech Translation with Pre-trained Models and Adapters: UPC at IWSLT 2021","date":"2021-05-10","arxiv_id":"2105.04512","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-speech-translation-via-cross-modal","slug":"end-to-end-speech-translation-via-cross-modal","title":"End-to-end Speech Translation via Cross-modal Progressive Training","date":"2021-04-21","arxiv_id":"2104.10380","repositories_listed":1,"syntology":null},{"url":"/paper/neurst-neural-speech-translation-toolkit","slug":"neurst-neural-speech-translation-toolkit","title":"NeurST: Neural Speech Translation Toolkit","date":"2020-12-18","arxiv_id":"2012.10018","repositories_listed":1,"syntology":null},{"url":"/paper/dual-decoder-transformer-for-joint-automatic","slug":"dual-decoder-transformer-for-joint-automatic","title":"Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation","date":"2020-11-02","arxiv_id":"2011.00747","repositories_listed":1,"syntology":null},{"url":"/paper/sdst-successive-decoding-for-speech-to-text","slug":"sdst-successive-decoding-for-speech-to-text","title":"Consecutive Decoding for Speech-to-text Translation","date":"2020-09-21","arxiv_id":"2009.09737","repositories_listed":1,"syntology":null},{"url":"/paper/ted-triple-supervision-decouples-end-to-end","slug":"ted-triple-supervision-decouples-end-to-end","title":"\"Listen, Understand and Translate\": Triple Supervision Decouples End-to-end Speech-to-text Translation","date":"2020-09-21","arxiv_id":"2009.09704","repositories_listed":1,"syntology":null},{"url":"/paper/contextualized-translation-of-automatically","slug":"contextualized-translation-of-automatically","title":"Contextualized Translation of Automatically Segmented Speech","date":"2020-08-05","arxiv_id":"2008.02270","repositories_listed":1,"syntology":null},{"url":"/paper/covost-a-diverse-multilingual-speech-to-text","slug":"covost-a-diverse-multilingual-speech-to-text","title":"CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus","date":"2020-02-04","arxiv_id":"2002.01320","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/covost-a-diverse-multilingual-speech-to-text#ran","syntology_url":"https://syntology.ai/paper/2002.01320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.01320"}},"official":{"repos":["facebookresearch/covost"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/flexibo-cost-aware-multi-objective","slug":"flexibo-cost-aware-multi-objective","title":"FlexiBO: A Decoupled Cost-Aware Multi-Objective Optimization Approach for Deep Neural Networks","date":"2020-01-18","arxiv_id":"2001.06588","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/flexibo-cost-aware-multi-objective#ran","syntology_url":"https://syntology.ai/paper/2001.06588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.06588"}},"official":{"repos":["softsys4ai/FlexiBO"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/synchronous-speech-recognition-and-speech-to","slug":"synchronous-speech-recognition-and-speech-to","title":"Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding","date":"2019-12-16","arxiv_id":"1912.07240","repositories_listed":1,"syntology":null},{"url":"/paper/direct-speech-to-speech-translation-with-a","slug":"direct-speech-to-speech-translation-with-a","title":"Direct speech-to-speech translation with a sequence-to-sequence model","date":"2019-04-12","arxiv_id":"1904.06037","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-on-high-resource-speech","slug":"pre-training-on-high-resource-speech","title":"Pre-training on high-resource speech recognition improves low-resource speech-to-text translation","date":"2018-09-05","arxiv_id":"1809.01431","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-automatic-speech-translation-of","slug":"end-to-end-automatic-speech-translation-of","title":"End-to-End Automatic Speech Translation of Audiobooks","date":"2018-02-12","arxiv_id":"1802.04200","repositories_listed":1,"syntology":null},{"url":"/paper/augmenting-librispeech-with-french","slug":"augmenting-librispeech-with-french","title":"Augmenting Librispeech with French Translations: A Multimodal Corpus for Direct Speech Translation Evaluation","date":"2018-02-09","arxiv_id":"1802.03142","repositories_listed":1,"syntology":null},{"url":"/paper/listen-and-translate-a-proof-of-concept-for","slug":"listen-and-translate-a-proof-of-concept-for","title":"Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation","date":"2016-12-06","arxiv_id":"1612.01744","repositories_listed":1,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/listen-and-translate-a-proof-of-concept-for#ran","syntology_url":"https://syntology.ai/paper/1612.01744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.01744"}},"official":{"repos":["eske/seq2seq"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":null,"slug":"end-to-end-speech-translation-for-low","title":"End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data","date":"2025-06-19","arxiv_id":"2506.16251","repositories_listed":0,"syntology":null},{"url":null,"slug":"s2st-omni-an-efficient-and-scalable","title":"S2ST-Omni: An Efficient and Scalable Multilingual Speech-to-Speech Translation Framework via Seamless Speech-Text Alignment and Streaming Speech Generation","date":"2025-06-11","arxiv_id":"2506.11160","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-language-and-modality-transfer-in","title":"Improving Language and Modality Transfer in Translation by Character-level Modeling","date":"2025-05-30","arxiv_id":"2505.24561","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-to-text-translation-with-phoneme","title":"Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios","date":"2025-05-30","arxiv_id":"2505.24691","repositories_listed":0,"syntology":null},{"url":null,"slug":"adast-dynamically-adapting-encoder-states-in-1","title":"AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation","date":"2025-03-18","arxiv_id":"2503.14185","repositories_listed":0,"syntology":null},{"url":null,"slug":"nexus-o-an-omni-perceptive-and-interactive","title":"Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision","date":"2025-02-26","arxiv_id":"2503.01879","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-speech-understanding-and-generation","title":"Balancing Speech Understanding and Generation Using Continual Pre-training for Codec-based Speech LLM","date":"2025-02-24","arxiv_id":"2502.16897","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-to-speech-translation-with","title":"Speech to Speech Translation with Translatotron: A State of the Art Review","date":"2025-02-09","arxiv_id":"2502.05980","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-end-to-end-is-overkill-rethinking","title":"When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation","date":"2025-02-01","arxiv_id":"2502.00377","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-real-is-your-real-time-simultaneous","title":"How \"Real\" is Your Real-Time Simultaneous Speech-to-Text Translation System?","date":"2024-12-24","arxiv_id":"2412.18495","repositories_listed":0,"syntology":null},{"url":null,"slug":"representation-purification-for-end-to-end","title":"Representation Purification for End-to-End Speech Translation","date":"2024-12-05","arxiv_id":"2412.04266","repositories_listed":0,"syntology":null},{"url":null,"slug":"isochrony-controlled-speech-to-text","title":"Isochrony-Controlled Speech-to-Text Translation: A study on translating from Sino-Tibetan to Indo-European Languages","date":"2024-11-11","arxiv_id":"2411.07387","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-is-more-than-words-do-speech-to-text","title":"Speech is More Than Words: Do Speech-to-Text Translation Systems Leverage Prosody?","date":"2024-10-31","arxiv_id":"2410.24019","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-survey-on-speech-large-language-models","title":"A Survey on Speech Large Language Models","date":"2024-10-24","arxiv_id":"2410.18908","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-biasing-to-improve-domain-specific","title":"Contextual Biasing to Improve Domain-specific Custom Vocabulary Audio Transcription without Explicit Fine-Tuning of Whisper Model","date":"2024-10-24","arxiv_id":"2410.18363","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-the-role-of-pretraining-in-direct","title":"Unveiling the Role of Pretraining in Direct Speech Translation","date":"2024-09-26","arxiv_id":"2409.18044","repositories_listed":0,"syntology":null},{"url":null,"slug":"finetuning-end-to-end-models-for-estonian","title":"Finetuning End-to-End Models for Estonian Conversational Spoken Language Translation","date":"2024-07-04","arxiv_id":"2407.03809","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-decoder-only-large-language","title":"Investigating Decoder-only Large Language Models for Speech-to-text Translation","date":"2024-07-03","arxiv_id":"2407.03169","repositories_listed":0,"syntology":null},{"url":null,"slug":"naist-simultaneous-speech-translation-system","title":"NAIST Simultaneous Speech Translation System for IWSLT 2024","date":"2024-06-30","arxiv_id":"2407.00826","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-achieve-high-quality-direct-speech-to","title":"Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data?","date":"2024-06-11","arxiv_id":"2406.07289","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-semantic-communications-for-speech-to","title":"Robust Semantic Communications for Speech Transmission","date":"2024-03-08","arxiv_id":"2403.05187","repositories_listed":0,"syntology":null},{"url":null,"slug":"compact-speech-translation-models-via","title":"Compact Speech Translation Models via Discrete Speech Units Pretraining","date":"2024-02-29","arxiv_id":"2402.19333","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-translation-with-speech-foundation","title":"Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?","date":"2024-02-19","arxiv_id":"2402.12025","repositories_listed":0,"syntology":null},{"url":null,"slug":"prosody-in-cascade-and-direct-speech-to-text","title":"Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases","date":"2024-02-01","arxiv_id":"2402.00632","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-monotonic-multihead-attention","title":"Efficient Monotonic Multihead Attention","date":"2023-12-07","arxiv_id":"2312.04515","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-speech-to-text-translation-a","title":"End-to-End Speech-to-Text Translation: A Survey","date":"2023-12-02","arxiv_id":"2312.01053","repositories_listed":0,"syntology":null},{"url":null,"slug":"cosmic-data-efficient-instruction-tuning-for","title":"COSMIC: Data Efficient Instruction-tuning For Speech In-Context Learning","date":"2023-11-03","arxiv_id":"2311.02248","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-stability-in-simultaneous-speech","title":"Improving Stability in Simultaneous Speech Translation: A Revision-Controllable Decoding Approach","date":"2023-10-06","arxiv_id":"2310.04399","repositories_listed":0,"syntology":null},{"url":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","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-modal-multi-tasking-for-speech-to-text","title":"Cross-Modal Multi-Tasking for Speech-to-Text Translation via Hard Parameter Sharing","date":"2023-09-27","arxiv_id":"2309.15826","repositories_listed":0,"syntology":null},{"url":null,"slug":"speechalign-a-framework-for-speech","title":"SpeechAlign: a Framework for Speech Translation Alignment Evaluation","date":"2023-09-20","arxiv_id":"2309.11585","repositories_listed":0,"syntology":null},{"url":null,"slug":"colld-contrastive-layer-to-layer-distillation","title":"CoLLD: Contrastive Layer-to-layer Distillation for Compressing Multilingual Pre-trained Speech Encoders","date":"2023-09-14","arxiv_id":"2309.07707","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-decoder-only-architecture-for-speech-to","title":"On decoder-only architecture for speech-to-text and large language model integration","date":"2023-07-08","arxiv_id":"2307.03917","repositories_listed":0,"syntology":null},{"url":null,"slug":"audiopalm-a-large-language-model-that-can","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","date":"2023-06-22","arxiv_id":"2306.12925","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-advances-in-direct-speech-to-text","title":"Recent Advances in Direct Speech-to-text Translation","date":"2023-06-20","arxiv_id":"2306.11646","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-cross-lingual-transfer-learning-for","title":"Improved Cross-Lingual Transfer Learning For Automatic Speech Translation","date":"2023-06-01","arxiv_id":"2306.00789","repositories_listed":0,"syntology":null}],"syntology_records":16,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"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)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":15,"papers_where_code_ran_first_page":"/task/speech-to-text-translation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":2,"url":"/task/speech-to-text-translation/papers/2","json":"/task/speech-to-text-translation/papers/2.json","rows":46},{"order":"ran","page":1,"of":1,"url":"/task/speech-to-text-translation/papers/ran/1","json":"/task/speech-to-text-translation/papers/ran/1.json","rows":15}],"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"832c6923305a60470c8a62cb3d5fc26e68a756b965a32ad046ae4c75a9534dd0","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}