{"url":"/task/streaming-target-sound-extraction","name":"Streaming Target Sound Extraction","slug":"streaming-target-sound-extraction","description_markdown":"This task is a variant of the [Target Sound Extraction](https://paperswithcode.com/task/target-sound-extraction) task, with the constraint of causal streaming inference. Aiming for an algorithmic latency of less than 20 ms, at each time step, streaming audio models operate on an input audio chunk of length less than 20 ms. The causal constraint means that the model only has the knowledge of past chunks and no future chunks.","categories":[{"name":"Audio","url":"/area/audio"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1,"papers_with_code":1,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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/streaming-target-sound-extraction-on","slug":"streaming-target-sound-extraction-on","dataset":"FSDSoundScapes","dataset_url":"/dataset/fsdsoundscapes","rows_in_archive":1,"metrics":["SI-SNRi"],"first_row_in_archive_order":{"model":"Waveformer","paper_title":"Real-Time Target Sound Extraction","paper_url":"/paper/real-time-target-sound-extraction","paper_date":"2022-11-04","arxiv_id":"2211.02250","code_links":[{"title":"vb000/waveformer","url":"https://github.com/vb000/waveformer"}],"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/fsdsoundscapes","name":"FSDSoundScapes","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/target-sound-extraction","name":"Target Sound Extraction"}],"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":1,"of":1,"tagged_in_all":1,"items":[{"url":"/paper/real-time-target-sound-extraction","title":"Real-Time Target Sound Extraction","date":"2022-11-04","arxiv_id":"2211.02250","repositories_listed":1,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":0}}],"syntology_records":1,"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":1,"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"}}