{"id":"https://openalex.org/W3015654783","doi":"https://doi.org/10.1109/icassp40776.2020.9053846","title":"Performance Study of a Convolutional Time-Domain Audio Separation Network for Real-Time Speech Denoising","display_name":"Performance Study of a Convolutional Time-Domain Audio Separation Network for Real-Time Speech Denoising","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015654783","doi":"https://doi.org/10.1109/icassp40776.2020.9053846","mag":"3015654783"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5091233806","display_name":"Samuel Sonning","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":true,"raw_author_name":"Samuel Sonning","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014795917","display_name":"Christian Sch\u00fcldt","orcid":"https://orcid.org/0000-0003-3439-0468"},"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":"Christian Schuldt","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065994318","display_name":"Hakan Erdo\u011fan","orcid":"https://orcid.org/0000-0003-3140-8642"},"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":"Hakan Erdogan","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053447215","display_name":"Scott Wisdom","orcid":"https://orcid.org/0000-0001-6671-1428"},"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":"Scott Wisdom","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091233806"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":3.0307,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92080316,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"831","last_page":"835"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7678318023681641},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.6081300973892212},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.5850979089736938},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.575810968875885},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5487764477729797},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.48388561606407166},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.47345489263534546},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.470624715089798},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.42459651827812195},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4106498956680298},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3885954022407532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3209354281425476},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10582208633422852}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678318023681641},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6081300973892212},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.5850979089736938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.575810968875885},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5487764477729797},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.48388561606407166},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.47345489263534546},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.470624715089798},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.42459651827812195},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4106498956680298},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3885954022407532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3209354281425476},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10582208633422852},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053846","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053846","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W317957491","https://openalex.org/W1482149378","https://openalex.org/W1563939609","https://openalex.org/W1596607002","https://openalex.org/W1728888090","https://openalex.org/W2101045344","https://openalex.org/W2103934944","https://openalex.org/W2121973264","https://openalex.org/W2140828385","https://openalex.org/W2291877678","https://openalex.org/W2773624778","https://openalex.org/W2892365986","https://openalex.org/W2962935966","https://openalex.org/W2963189033","https://openalex.org/W2963341071","https://openalex.org/W2963452667","https://openalex.org/W2963902628","https://openalex.org/W2964058413","https://openalex.org/W2972359262","https://openalex.org/W2973133192","https://openalex.org/W3147539069","https://openalex.org/W6675521023","https://openalex.org/W6751512325","https://openalex.org/W6754743415"],"related_works":["https://openalex.org/W3110702597","https://openalex.org/W2073713056","https://openalex.org/W2125620709","https://openalex.org/W2110441383","https://openalex.org/W2045932760","https://openalex.org/W2326878701","https://openalex.org/W4293864700","https://openalex.org/W2184228419","https://openalex.org/W1872350411","https://openalex.org/W2136112003"],"abstract_inverted_index":{"Time-domain":[0],"audio":[1],"separation":[2,29],"networks":[3],"based":[4,22],"on":[5,23],"dilated":[6],"temporal":[7],"convolutions":[8],"have":[9],"recently":[10],"been":[11],"shown":[12],"to":[13,18,73],"perform":[14],"very":[15],"well":[16],"compared":[17,72],"methods":[19],"that":[20,83],"are":[21,69],"a":[24,48,56,77,84,93,101],"time-frequency":[25,36],"representation":[26],"in":[27,55,90],"speech":[28,53],"tasks,":[30],"even":[31,111],"outperforming":[32],"an":[33],"oracle":[34],"binary":[35],"mask":[37],"of":[38,46,67,76,87,103,110],"the":[39,44,74,88,108],"speakers.":[40],"This":[41],"paper":[42],"investigates":[43],"performance":[45,91],"such":[47],"time-domain":[49],"network":[50],"(Conv-TasNet)":[51],"for":[52,114],"denoising":[54],"real-time":[57,116],"setting,":[58],"comparing":[59],"various":[60],"parameter":[61],"settings.":[62],"Most":[63],"importantly,":[64],"different":[65],"amounts":[66],"lookahead":[68,102],"evaluated":[70],"and":[71,95],"baseline":[75],"fully":[78],"causal":[79,94],"model.":[80],"We":[81],"show":[82],"large":[85],"part":[86],"increase":[89],"between":[92],"non-causal":[96],"model":[97],"is":[98],"achieved":[99],"with":[100],"only":[104],"20":[105],"milliseconds,":[106],"demonstrating":[107],"usefulness":[109],"small":[112],"lookaheads":[113],"many":[115],"applications.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}