{"id":"https://openalex.org/W2407277936","doi":"https://doi.org/10.1109/icassp.2016.7472644","title":"Factored spatial and spectral multichannel raw waveform CLDNNs","display_name":"Factored spatial and spectral multichannel raw waveform CLDNNs","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2407277936","doi":"https://doi.org/10.1109/icassp.2016.7472644","mag":"2407277936"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"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":"Tara N. Sainath","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, 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., New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"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 W. Wilson","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000078382","display_name":"Arun Narayanan","orcid":"https://orcid.org/0009-0008-3325-8928"},"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":"Arun Narayanan","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"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":"Michiel Bacchiani","raw_affiliation_strings":["Google, Inc., New York, NY, USA"],"affiliations":[{"raw_affiliation_string":"Google, Inc., New York, NY, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070513394"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":10.4375,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.98665886,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5075","last_page":"5079"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/computer-science","display_name":"Computer science","score":0.7689553499221802},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.718799889087677},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5398871302604675},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5335085391998291},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4826841652393341},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.48065459728240967},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47389617562294006},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43741536140441895},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3858516216278076},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14452782273292542},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07536125183105469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7689553499221802},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.718799889087677},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5398871302604675},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5335085391998291},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4826841652393341},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.48065459728240967},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47389617562294006},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43741536140441895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3858516216278076},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14452782273292542},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07536125183105469},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1499999342","https://openalex.org/W1533861849","https://openalex.org/W1542280630","https://openalex.org/W1600744878","https://openalex.org/W2035846950","https://openalex.org/W2060108923","https://openalex.org/W2061074721","https://openalex.org/W2099655464","https://openalex.org/W2117678320","https://openalex.org/W2119203697","https://openalex.org/W2121573996","https://openalex.org/W2130361043","https://openalex.org/W2141411743","https://openalex.org/W2168231600","https://openalex.org/W2290318471","https://openalex.org/W2398826216","https://openalex.org/W2962719052","https://openalex.org/W2964138484","https://openalex.org/W4249052411","https://openalex.org/W6631943919","https://openalex.org/W6684859321","https://openalex.org/W6712560600"],"related_works":["https://openalex.org/W1974895211","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2056136368","https://openalex.org/W2374664672","https://openalex.org/W4367555392","https://openalex.org/W2538520412","https://openalex.org/W2883092465"],"abstract_inverted_index":{"Multichannel":[0],"ASR":[1],"systems":[2],"commonly":[3],"separate":[4,50],"speech":[5],"enhancement,":[6],"including":[7],"localization,":[8],"beamforming":[9,26],"and":[10,27,101,127,134],"postfiltering,":[11,66],"from":[12,110],"acoustic":[13,23],"modeling.":[14],"Recently,":[15],"we":[16,44,56,68,88,123],"explored":[17],"doing":[18],"multichannel":[19,136],"enhancement":[20],"jointly":[21],"with":[22,84],"modeling,":[24],"where":[25,67],"frequency":[28],"decomposition":[29],"was":[30],"folded":[31],"into":[32,49],"one":[33],"layer":[34],"of":[35],"the":[36,53,70,85,107],"neural":[37],"network":[38,71],"[1,":[39],"2].":[40],"In":[41,118],"this":[42],"paper,":[43],"explore":[45,57],"factoring":[46],"these":[47],"operations":[48],"layers":[51],"in":[52,95],"network.":[54],"Furthermore,":[55],"using":[58],"multi-task":[59],"learning":[60],"(MTL)":[61],"as":[62,76,78],"a":[63,91,98,102,113],"proxy":[64],"for":[65],"train":[69],"to":[72],"predict":[73],"\"clean\"":[74],"features":[75],"well":[77],"context-dependent":[79],"states.":[80],"We":[81],"find":[82],"that":[83],"factored":[86],"architecture,":[87],"can":[89,124],"achieve":[90,125],"10%":[92],"relative":[93,104,129],"improvement":[94,105],"WER":[96],"over":[97,106,131],"single":[99,132],"channel":[100,133],"5%":[103],"unfactored":[108,135],"model":[109],"[1]":[111],"on":[112],"2,000-hour":[114],"Voice":[115],"Search":[116],"task.":[117],"addition,":[119],"by":[120],"incorporating":[121],"MTL,":[122],"11%":[126],"7%":[128],"improvements":[130],"models,":[137],"respectively.":[138]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":7}],"updated_date":"2026-04-04T06:10:10.580331","created_date":"2025-10-10T00:00:00"}