{"id":"https://openalex.org/W2973062255","doi":"https://doi.org/10.21437/interspeech.2019-1101","title":"VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking","display_name":"VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2973062255","doi":"https://doi.org/10.21437/interspeech.2019-1101","mag":"2973062255"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-1101","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100418252","display_name":"Quan Wang","orcid":"https://orcid.org/0000-0002-2508-6301"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Quan Wang","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047091215","display_name":"Hannah Muckenhirn","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Hannah Muckenhirn","raw_affiliation_strings":["Idiap Research Institute, Switzerland","EPFL, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"EPFL, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087313939","display_name":"Kevin Wilson","orcid":"https://orcid.org/0000-0001-9141-2219"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Wilson","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006917911","display_name":"Prashant Sridhar","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prashant Sridhar","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035558261","display_name":"Zelin Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zelin Wu","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026650852","display_name":"Rif A. Saurous","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rif A. Saurous","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103273436","display_name":"Ron J. Weiss","orcid":"https://orcid.org/0000-0003-2010-4053"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron J. Weiss","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102792436","display_name":"Jia Ye","orcid":"https://orcid.org/0000-0002-8000-4911"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ye Jia","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050898122","display_name":"Ignacio L\u00f3pez Moreno","orcid":"https://orcid.org/0000-0002-0900-3473"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ignacio Lopez Moreno","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5100418252"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":30.72,"has_fulltext":false,"cited_by_count":339,"citation_normalized_percentile":{"value":0.99902611,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2728","last_page":"2732"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9606000185012817,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9072123169898987},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7103824615478516},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5644961595535278},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.5515633225440979},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.06668311357498169}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9072123169898987},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7103824615478516},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5644961595535278},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5515633225440979},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.06668311357498169},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2019-1101","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-1101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2460742184","https://openalex.org/W2527729766","https://openalex.org/W2545177271","https://openalex.org/W2558649592","https://openalex.org/W2612601884","https://openalex.org/W2726515241","https://openalex.org/W2749510669","https://openalex.org/W2787692317","https://openalex.org/W2808631503","https://openalex.org/W2808706139","https://openalex.org/W2891833136","https://openalex.org/W2896538040","https://openalex.org/W2936184970","https://openalex.org/W2963470929","https://openalex.org/W2963902628","https://openalex.org/W2964171275","https://openalex.org/W2964238697","https://openalex.org/W3123318516"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W2011227383","https://openalex.org/W2065606036","https://openalex.org/W2973062255","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"In":[0],"this":[1,31],"paper,":[2],"we":[3],"present":[4],"a":[5,13,23,63],"novel":[6],"system":[7,65],"that":[8,43,51],"separates":[9],"the":[10,27,68],"voice":[11],"of":[12,22],"target":[14,28],"speaker":[15,40,57],"from":[16,26],"multi-speaker":[17,73],"signals,":[18,74],"by":[19,32],"making":[20],"use":[21],"reference":[24],"signal":[25],"speaker.We":[29],"achieve":[30],"training":[33],"two":[34],"separate":[35],"neural":[36],"networks:":[37],"(1)":[38],"A":[39,47],"recognition":[41,70],"network":[42,50],"produces":[44,62],"speaker-discriminative":[45],"embeddings;(2)":[46],"spectrogram":[48,55],"masking":[49],"takes":[52],"both":[53],"noisy":[54],"and":[56,61],"embedding":[58],"as":[59],"input,":[60],"mask.Our":[64],"significantly":[66],"reduces":[67],"speech":[69],"WER":[71,77],"on":[72,79],"with":[75],"minimal":[76],"degradation":[78],"single-speaker":[80],"signals.":[81]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":36},{"year":2024,"cited_by_count":52},{"year":2023,"cited_by_count":57},{"year":2022,"cited_by_count":49},{"year":2021,"cited_by_count":68},{"year":2020,"cited_by_count":46},{"year":2019,"cited_by_count":21}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}