{"url":"/method/voicefilter-lite","slug":"voicefilter-lite","name":"VoiceFilter-Lite","full_name":"VoiceFilter-Lite","full_name_withheld":false,"description_markdown":"**VoiceFilter-Lite** is a single-channel source separation model that runs on the device to preserve only the speech signals from a target user, as part of a streaming speech recognition system. In this architecture, the voice filtering model operates as a frame-by-frame frontend signal processor to enhance the features consumed by the speech recognizer, without reconstructing audio signals from the features. The key contributions are (1) A system to perform speech separation directly on ASR input features; (2) An asymmetric loss function to penalize oversuppression during training, to make the model harmless under various acoustic environments, (3) An adaptive suppression strength mechanism to adapt to different noise conditions.","description_state":"present","introduced_year":null,"introduced_by":{"title":"VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognition","paper":"/paper/voicefilter-lite-streaming-targeted-voice","first_author":"Quan Wang","n_authors":11,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/voicefilter-lite-streaming-targeted-voice"},"source":{"url":"https://arxiv.org/abs/2009.04323v1","title":"VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognition","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Audio","area_id":"audio","collection":"Speech Separation Models","url":"/methods/category/speech-separation-models","pwc_aliases":["speech-separation"]}],"n_papers_tagged":3,"archive_num_papers":3,"papers_newest_first":[{"paper":null,"title":"Closing the Gap between Single-User and Multi-User VoiceFilter-Lite","date":"2022-02-24","arxiv_id":"2202.12169","n_code_links":0,"syntology":null},{"paper":null,"title":"Multi-user VoiceFilter-Lite via Attentive Speaker Embedding","date":"2021-07-02","arxiv_id":"2107.01201","n_code_links":0,"syntology":null},{"paper":"/paper/voicefilter-lite-streaming-targeted-voice","title":"VoiceFilter-Lite: Streaming Targeted Voice Separation for On-Device Speech Recognition","date":"2020-09-09","arxiv_id":"2009.04323","n_code_links":2,"syntology":null}],"papers_shown":3,"tasks":[{"task":"/task/speech-recognition","name":"Speech Recognition","papers":3},{"task":"/task/speech-recognition-1","name":"speech-recognition","papers":3},{"task":"/task/speaker-verification","name":"Speaker Verification","papers":2},{"task":"/task/automatic-speech-recognition-2","name":"Automatic Speech Recognition","papers":1},{"task":"/task/automatic-speech-recognition","name":"Automatic Speech Recognition (ASR)","papers":1},{"task":null,"name":"CPU","papers":1},{"task":"/task/task-2","name":"Task 2","papers":1},{"task":"/task/text-independent-speaker-verification","name":"Text-Independent Speaker Verification","papers":1}],"tasks_shown":8,"n_tasks":8,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2022","papers":1}],"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/voicefilter-lite"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}