{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/permutation-invariant-training-of-deep-models","title":"Permutation Invariant Training of Deep Models for Speaker-Independent Multi-talker Speech Separation","arxiv_id":"1607.00325","date":"2016-07-01","proceeding":null,"authors":["Dong Yu","Morten Kolbæk","Zheng-Hua Tan","Jesper Jensen"],"abstract":"We propose a novel deep learning model, which supports permutation invariant\ntraining (PIT), for speaker independent multi-talker speech separation,\ncommonly known as the cocktail-party problem. Different from most of the prior\narts that treat speech separation as a multi-class regression problem and the\ndeep clustering technique that considers it a segmentation (or clustering)\nproblem, our model optimizes for the separation regression error, ignoring the\norder of mixing sources. This strategy cleverly solves the long-lasting label\npermutation problem that has prevented progress on deep learning based\ntechniques for speech separation. Experiments on the equal-energy mixing setup\nof a Danish corpus confirms the effectiveness of PIT. We believe improvements\nbuilt upon PIT can eventually solve the cocktail-party problem and enable\nreal-world adoption of, e.g., automatic meeting transcription and multi-party\nhuman-computer interaction, where overlapping speech is common.","url_abs":"http://arxiv.org/abs/1607.00325v2","url_pdf":"http://arxiv.org/pdf/1607.00325v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"permutation-invariant-training-of-deep-models","repo_url":"https://github.com/JusperLee/UtterancePIT-Speech-Separation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"deep-clustering","task_name":"Deep Clustering"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"speech-separation","task_name":"Speech Separation"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"upit","method_name":"uPIT"}],"datasets_introduced":[],"methods_introduced":[{"slug":"upit","name":"uPIT","full_name":"utterance level permutation invariant training"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1607.00325","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}