{"url":"/method/upit","slug":"upit","name":"uPIT","full_name":"utterance level permutation invariant training","full_name_withheld":false,"description_markdown":null,"description_state":"absent","introduced_year":null,"introduced_by":{"title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","paper":"/paper/permutation-invariant-training-of-deep-models","first_author":"Dong Yu","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/permutation-invariant-training-of-deep-models"},"source":{"url":"http://arxiv.org/abs/1607.00325v2","title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Loss Functions","url":"/methods/category/loss-functions","pwc_aliases":[]}],"n_papers_tagged":7,"archive_num_papers":7,"papers_newest_first":[{"paper":"/paper/graph-pit-generalized-permutation-invariant","title":"Graph-PIT: Generalized permutation invariant training for continuous separation of arbitrary numbers of speakers","date":"2021-07-30","arxiv_id":"2107.14446","n_code_links":1,"syntology":null},{"paper":"/paper/speeding-up-permutation-invariant-training","title":"Speeding Up Permutation Invariant Training for Source Separation","date":"2021-07-30","arxiv_id":"2107.14445","n_code_links":1,"syntology":null},{"paper":"/paper/voice-separation-with-an-unknown-number-of","title":"Voice Separation with an Unknown Number of Multiple Speakers","date":"2020-02-29","arxiv_id":"2003.01531","n_code_links":4,"syntology":{"ran":10,"of":13,"unverified":3,"pointer_only":9}},{"paper":null,"title":"Utterance-level Permutation Invariant Training with Latency-controlled BLSTM for Single-channel Multi-talker Speech Separation","date":"2019-12-25","arxiv_id":"1912.11613","n_code_links":0,"syntology":null},{"paper":null,"title":"Discriminative Learning for Monaural Speech Separation Using Deep Embedding Features","date":"2019-07-23","arxiv_id":"1907.09884","n_code_links":0,"syntology":null},{"paper":"/paper/multi-talker-speech-separation-with-utterance","title":"Multi-talker Speech Separation with Utterance-level Permutation Invariant Training of Deep Recurrent Neural Networks","date":"2017-03-18","arxiv_id":"1703.06284","n_code_links":3,"syntology":{"ran":1,"of":3,"unverified":2,"pointer_only":3}},{"paper":"/paper/permutation-invariant-training-of-deep-models","title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","date":"2016-07-01","arxiv_id":"1607.00325","n_code_links":1,"syntology":null}],"papers_shown":7,"tasks":[{"task":"/task/speech-separation","name":"Speech Separation","papers":6},{"task":"/task/clustering","name":"Clustering","papers":3},{"task":"/task/deep-clustering","name":"Deep Clustering","papers":3},{"task":"/task/deep-learning","name":"Deep Learning","papers":1},{"task":"/task/regression-1","name":"regression","papers":1}],"tasks_shown":5,"n_tasks":5,"usage_by_year":[{"year":"2016","papers":1},{"year":"2017","papers":1},{"year":"2019","papers":2},{"year":"2020","papers":1},{"year":"2021","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/upit"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}