{"id":"https://openalex.org/W2900177268","doi":"https://doi.org/10.1109/iwaenc.2018.8521347","title":"Exploring Tradeoffs in Models for Low-Latency Speech Enhancement","display_name":"Exploring Tradeoffs in Models for Low-Latency Speech Enhancement","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2900177268","doi":"https://doi.org/10.1109/iwaenc.2018.8521347","mag":"2900177268"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2018.8521347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.07030","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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":true,"raw_author_name":"Kevin Wilson","raw_affiliation_strings":["Google Research, Google Chrome Audio","Google Chrome Audio, Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research, Google Chrome Audio","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Chrome Audio, Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016309279","display_name":"Michael Chinen","orcid":"https://orcid.org/0000-0003-4154-2132"},"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":"Michael Chinen","raw_affiliation_strings":["Google Research, Google Chrome Audio","Google Chrome Audio, Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research, Google Chrome Audio","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Chrome Audio, Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001338678","display_name":"Jeremy Thorpe","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":"Jeremy Thorpe","raw_affiliation_strings":["Google Research, Google Chrome Audio","Google Chrome Audio, Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research, Google Chrome Audio","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Chrome Audio, Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013234773","display_name":"Brian Patton","orcid":"https://orcid.org/0000-0001-8222-4419"},"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":"Brian Patton","raw_affiliation_strings":["Google Research, Google Chrome Audio","Google Chrome Audio, Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research, Google Chrome Audio","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Chrome Audio, Google Research","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 Hershey","raw_affiliation_strings":["Google Research, Google Chrome Audio","Google Chrome Audio, Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research, Google Chrome Audio","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Chrome Audio, Google Research","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 Research, Google Chrome Audio","Google Chrome Audio, Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research, Google Chrome Audio","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Chrome Audio, Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070792118","display_name":"Jan Skoglund","orcid":"https://orcid.org/0009-0008-0167-4628"},"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":"Jan Skoglund","raw_affiliation_strings":["Google Research, Google Chrome Audio","Google Chrome Audio, Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research, Google Chrome Audio","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Chrome Audio, Google Research","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026382065","display_name":"Richard F. Lyon","orcid":"https://orcid.org/0000-0003-2348-811X"},"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":"Richard F. Lyon","raw_affiliation_strings":["Google Research, Google Chrome Audio","Google Chrome Audio, Google Research"],"affiliations":[{"raw_affiliation_string":"Google Research, Google Chrome Audio","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Chrome Audio, Google Research","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5087313939"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.4975,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65194958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"366","last_page":"370"},"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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6700432300567627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6662389636039734},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6492622494697571},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5960618853569031},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5958065390586853},{"id":"https://openalex.org/keywords/decibel","display_name":"Decibel","score":0.5581132173538208},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5488817691802979},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4738464951515198},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4702429175376892},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4539510905742645},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4361862540245056},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2965790629386902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23797056078910828},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1441335380077362},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09588941931724548},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0752570629119873}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6700432300567627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662389636039734},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6492622494697571},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5960618853569031},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5958065390586853},{"id":"https://openalex.org/C204358264","wikidata":"https://www.wikidata.org/wiki/Q5329","display_name":"Decibel","level":2,"score":0.5581132173538208},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5488817691802979},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4738464951515198},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4702429175376892},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4539510905742645},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4361862540245056},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2965790629386902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23797056078910828},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1441335380077362},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09588941931724548},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0752570629119873},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iwaenc.2018.8521347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521347","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.07030","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.07030","pdf_url":"https://arxiv.org/pdf/1811.07030","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2900177268","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1811.07030","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1811.07030","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.07030","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.07030","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.07030","pdf_url":"https://arxiv.org/pdf/1811.07030","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2900177268.pdf","grobid_xml":"https://content.openalex.org/works/W2900177268.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1897240248","https://openalex.org/W2101045344","https://openalex.org/W2127851351","https://openalex.org/W2156798212","https://openalex.org/W2291877678","https://openalex.org/W2364134690","https://openalex.org/W2515930231","https://openalex.org/W2732547613","https://openalex.org/W2773624778","https://openalex.org/W6726205927"],"related_works":["https://openalex.org/W2963902628","https://openalex.org/W3088159194","https://openalex.org/W3098606562","https://openalex.org/W2994785103","https://openalex.org/W3199713199","https://openalex.org/W2963954250","https://openalex.org/W2797972631","https://openalex.org/W3209490467","https://openalex.org/W3160973314","https://openalex.org/W3164736513","https://openalex.org/W3027637851","https://openalex.org/W3028019732","https://openalex.org/W2591810467","https://openalex.org/W2221901388","https://openalex.org/W3003901600","https://openalex.org/W3128709077","https://openalex.org/W3015654783","https://openalex.org/W2944162086","https://openalex.org/W3091570562","https://openalex.org/W2994988791"],"abstract_inverted_index":{"We":[0,36],"explore":[1],"a":[2],"variety":[3],"of":[4,63,74],"neural":[5],"networks":[6],"configurations":[7],"for":[8],"one-":[9],"and":[10,44,50],"two-channel":[11],"spectrogram-mask-based":[12],"speech":[13,26],"enhancement.":[14],"Our":[15],"best":[16,65,84],"model":[17],"improves":[18],"on":[19,23,57],"previous":[20],"state-of-the-art":[21],"performance":[22,49,81],"the":[24],"CHiME2":[25],"enhancement":[27,48],"task":[28],"by":[29],"0.4":[30],"decibels":[31],"in":[32],"signal-to-distortion":[33],"ratio":[34],"(SDR).":[35],"examine":[37],"trade-offs":[38],"such":[39],"as":[40],"non-causal":[41],"look-ahead,":[42],"computation,":[43],"parameter":[45],"count":[46],"versus":[47],"find":[51,70],"that":[52,71],"zero-look-ahead":[53],"models":[54],"can":[55],"achieve,":[56],"average,":[58],"within":[59],"0.03":[60],"dB":[61],"SDR":[62],"our":[64,83],"bidirectional":[66,85],"model.":[67,86],"Further,":[68],"we":[69],"200":[72],"milliseconds":[73],"look-ahead":[75],"is":[76],"sufficient":[77],"to":[78,82],"achieve":[79],"equivalent":[80]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}