{"url":"/task/automatic-speech-translation","name":"automatic-speech-translation","slug":"automatic-speech-translation","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":23,"papers_with_code":7,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":3,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/fleurs","name":"FLEURS","full_name":"Few-shot Learning Evaluation of Universal Representations of Speech","num_papers_in_archive":141},{"url":"/dataset/covost","name":"CoVoST","full_name":"","num_papers_in_archive":34},{"url":"/dataset/medibeng","name":"MediBeng","full_name":"Synthetic Code-Switched Bengali-English Speech Conversations for Healthcare Applications","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":7,"of":7,"tagged_in_all":23,"items":[{"url":"/paper/word-level-timestamp-generation-for-automatic","title":"Word Level Timestamp Generation for Automatic Speech Recognition and Translation","date":"2025-05-21","arxiv_id":"2505.15646","repositories_listed":1,"syntology":null},{"url":"/paper/bhasaanuvaad-a-speech-translation-dataset-for","title":"BhasaAnuvaad: A Speech Translation Dataset for 13 Indian Languages","date":"2024-11-07","arxiv_id":"2411.04699","repositories_listed":1,"syntology":null},{"url":"/paper/mooer-llm-based-speech-recognition-and","title":"MooER: LLM-based Speech Recognition and Translation Models from Moore Threads","date":"2024-08-09","arxiv_id":"2408.05101","repositories_listed":1,"syntology":null},{"url":"/paper/seamless-multilingual-expressive-and","title":"Seamless: Multilingual Expressive and Streaming Speech Translation","date":"2023-12-08","arxiv_id":"2312.05187","repositories_listed":1,"syntology":null},{"url":"/paper/improving-end-to-end-speech-translation-by-2","title":"Improving End-to-End Speech Translation by Imitation-Based Knowledge Distillation with Synthetic Transcripts","date":"2023-07-17","arxiv_id":"2307.08426","repositories_listed":1,"syntology":null},{"url":"/paper/skinaugment-auto-encoding-speaker-conversions","title":"SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech Translation","date":"2020-02-27","arxiv_id":"2002.12231","repositories_listed":1,"syntology":null},{"url":"/paper/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}],"syntology_records":0,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}