{"url":"/task/automatic-lyrics-transcription","name":"Automatic Lyrics Transcription","slug":"automatic-lyrics-transcription","description_markdown":"Automatic Lyrics Transcription is the task of transcribing singing voice from audio into text.","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":12,"papers_with_code":9,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"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":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/automatic-lyrics-transcription-on-jam-alt-1","slug":"automatic-lyrics-transcription-on-jam-alt-1","dataset":"Jam-ALT English","dataset_url":"/dataset/jam-alt","rows_in_archive":18,"metrics":["Word Error Rate (WER)","Case-Sensitive Word Error Rate","Case Error Rate","Punctuation F-1","Parenthesis F-1","Line break F-1","Section break F-1"],"first_row_in_archive_order":{"model":"AudioShake v3","paper_title":"Lyrics Transcription for Humans: A Readability-Aware Benchmark","paper_url":"/paper/lyrics-transcription-for-humans-a-readability","paper_date":"2024-07-30","arxiv_id":"2408.06370","code_links":[{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"}],"syntology":null}},{"leaderboard":"/sota/automatic-lyrics-transcription-on-jam-alt","slug":"automatic-lyrics-transcription-on-jam-alt","dataset":"Jam-ALT","dataset_url":"/dataset/jam-alt","rows_in_archive":16,"metrics":["Word Error Rate (WER)","Case-Sensitive Word Error Rate","Case Error Rate","Punctuation F1","Parenthesis F-1","Line break F1","Section break F1"],"first_row_in_archive_order":{"model":"AudioShake v3","paper_title":"Lyrics Transcription for Humans: A Readability-Aware Benchmark","paper_url":"/paper/lyrics-transcription-for-humans-a-readability","paper_date":"2024-07-30","arxiv_id":"2408.06370","code_links":[{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"}],"syntology":null}},{"leaderboard":"/sota/automatic-lyrics-transcription-on-jam-alt-2","slug":"automatic-lyrics-transcription-on-jam-alt-2","dataset":"Jam-ALT Spanish","dataset_url":"/dataset/jam-alt","rows_in_archive":16,"metrics":["Word Error Rate (WER)","Case-Sensitive Word Error Rate","Case Error Rate","Punctuation F-1","Parenthesis F-1","Line break F-1","Section break F-1"],"first_row_in_archive_order":{"model":"AudioShake v3","paper_title":"Lyrics Transcription for Humans: A Readability-Aware Benchmark","paper_url":"/paper/lyrics-transcription-for-humans-a-readability","paper_date":"2024-07-30","arxiv_id":"2408.06370","code_links":[{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"}],"syntology":null}},{"leaderboard":"/sota/automatic-lyrics-transcription-on-jam-alt-3","slug":"automatic-lyrics-transcription-on-jam-alt-3","dataset":"Jam-ALT German","dataset_url":"/dataset/jam-alt","rows_in_archive":16,"metrics":["Word Error Rate (WER)","Case-Sensitive Word Error Rate","Case Error Rate","Punctuation F-1","Parenthesis F-1","Line break F-1","Section break F-1"],"first_row_in_archive_order":{"model":"AudioShake v3","paper_title":"Lyrics Transcription for Humans: A Readability-Aware Benchmark","paper_url":"/paper/lyrics-transcription-for-humans-a-readability","paper_date":"2024-07-30","arxiv_id":"2408.06370","code_links":[{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"}],"syntology":null}},{"leaderboard":"/sota/automatic-lyrics-transcription-on-jam-alt-4","slug":"automatic-lyrics-transcription-on-jam-alt-4","dataset":"Jam-ALT French","dataset_url":"/dataset/jam-alt","rows_in_archive":16,"metrics":["Word Error Rate (WER)","Case-Sensitive Word Error Rate","Case Error Rate","Punctuation F-1","Parenthesis F-1","Line break F-1","Section break F-1"],"first_row_in_archive_order":{"model":"AudioShake v3","paper_title":"Lyrics Transcription for Humans: A Readability-Aware Benchmark","paper_url":"/paper/lyrics-transcription-for-humans-a-readability","paper_date":"2024-07-30","arxiv_id":"2408.06370","code_links":[{"title":"audioshake/alt-eval","url":"https://github.com/audioshake/alt-eval"}],"syntology":null}}],"datasets":[{"url":"/dataset/jam-alt","name":"Jam-ALT","full_name":"JamALT: A Formatting-Aware Lyrics Transcription Benchmark","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/speech-recognition","name":"Speech Recognition"}],"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":9,"of":9,"tagged_in_all":12,"items":[{"url":"/paper/mstre-net-multistreaming-acoustic-modeling","title":"MSTRE-Net: Multistreaming Acoustic Modeling for Automatic Lyrics Transcription","date":"2021-08-05","arxiv_id":"2108.02625","repositories_listed":2,"syntology":null},{"url":"/paper/automatic-lyrics-transcription-using-dilated","title":"Automatic Lyrics Transcription using Dilated Convolutional Neural Networks with Self-Attention","date":"2020-07-13","arxiv_id":"2007.06486","repositories_listed":2,"syntology":null},{"url":"/paper/lyrics-transcription-for-humans-a-readability","title":"Lyrics Transcription for Humans: A Readability-Aware Benchmark","date":"2024-07-30","arxiv_id":"2408.06370","repositories_listed":1,"syntology":null},{"url":"/paper/towards-building-an-end-to-end-multilingual","title":"Towards Building an End-to-End Multilingual Automatic Lyrics Transcription Model","date":"2024-06-25","arxiv_id":"2406.17618","repositories_listed":1,"syntology":null},{"url":"/paper/jam-alt-a-formatting-aware-lyrics","title":"Jam-ALT: A Formatting-Aware Lyrics Transcription Benchmark","date":"2023-11-23","arxiv_id":"2311.13987","repositories_listed":1,"syntology":null},{"url":"/paper/adapting-pretrained-speech-model-for-mandarin","title":"Adapting pretrained speech model for Mandarin lyrics transcription and alignment","date":"2023-11-21","arxiv_id":"2311.12488","repositories_listed":1,"syntology":null},{"url":"/paper/lyricwhiz-robust-multilingual-zero-shot","title":"LyricWhiz: Robust Multilingual Zero-shot Lyrics Transcription by Whispering to ChatGPT","date":"2023-06-29","arxiv_id":"2306.17103","repositories_listed":1,"syntology":null},{"url":"/paper/music-robust-automatic-lyrics-transcription","title":"Music-robust Automatic Lyrics Transcription of Polyphonic Music","date":"2022-04-07","arxiv_id":"2204.03306","repositories_listed":1,"syntology":null},{"url":"/paper/computational-pronunciation-analysis-in-sung","title":"Computational Pronunciation Analysis in Sung Utterances","date":"2021-06-21","arxiv_id":"2106.10977","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"}}