{"id":"https://openalex.org/W1485222997","doi":"https://doi.org/10.1109/icassp.2015.7178863","title":"Automatic gain control and multi-style training for robust small-footprint keyword spotting with deep neural networks","display_name":"Automatic gain control and multi-style training for robust small-footprint keyword spotting with deep neural networks","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1485222997","doi":"https://doi.org/10.1109/icassp.2015.7178863","mag":"1485222997"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5032640894","display_name":"Rohit Prabhavalkar","orcid":"https://orcid.org/0000-0001-5331-6058"},"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":"Rohit Prabhavalkar","raw_affiliation_strings":["Google Inc., Mountain View, USA","Google Inc. , Mountain View, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc. , Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054213481","display_name":"Raziel \u00c1lvarez","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":"Raziel Alvarez","raw_affiliation_strings":["Google Inc., Mountain View, USA","Google Inc. , Mountain View, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc. , Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090570382","display_name":"Carolina Parada","orcid":"https://orcid.org/0009-0000-7772-4646"},"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":"Carolina Parada","raw_affiliation_strings":["Google Inc., Mountain View, USA","Google Inc. , Mountain View, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc. , Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110716768","display_name":"Preetum Nakkiran","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Preetum Nakkiran","raw_affiliation_strings":["Department of EECS, University of California, Berkeley, USA","University of California, Berkeley, Department of EECS, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of EECS, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley, Department of EECS, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","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":false,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["Google Inc., Mountain View, USA","Google Inc. , Mountain View, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Inc., Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google Inc. , Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":96,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4704","last_page":"4708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.9088658094406128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7939314842224121},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7233050465583801},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.6535016298294067},{"id":"https://openalex.org/keywords/footprint","display_name":"Footprint","score":0.5941047072410583},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5865663290023804},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5223537683486938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5098142027854919},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.461218923330307},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.45611828565597534},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41236260533332825},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3280869722366333}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.9088658094406128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939314842224121},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7233050465583801},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.6535016298294067},{"id":"https://openalex.org/C132943942","wikidata":"https://www.wikidata.org/wiki/Q2562511","display_name":"Footprint","level":2,"score":0.5941047072410583},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5865663290023804},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5223537683486938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5098142027854919},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.461218923330307},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.45611828565597534},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41236260533332825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3280869722366333},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178863","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178863","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/W654137760","https://openalex.org/W1536984051","https://openalex.org/W1734538896","https://openalex.org/W1974205368","https://openalex.org/W2034940213","https://openalex.org/W2035424729","https://openalex.org/W2035576074","https://openalex.org/W2067392428","https://openalex.org/W2121814440","https://openalex.org/W2151244813","https://openalex.org/W2161803517","https://openalex.org/W2168231600","https://openalex.org/W2171019095","https://openalex.org/W2296516251","https://openalex.org/W2296748324","https://openalex.org/W2406801736","https://openalex.org/W2442329935","https://openalex.org/W2499961611","https://openalex.org/W2928556070","https://openalex.org/W2964138484","https://openalex.org/W6684859321","https://openalex.org/W6697318756","https://openalex.org/W6697811694","https://openalex.org/W6718561954"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W2545741539","https://openalex.org/W3206647229","https://openalex.org/W4286904253","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2117995638"],"abstract_inverted_index":{"We":[0,28],"explore":[1],"techniques":[2,78],"to":[3,41,81,88],"improve":[4],"the":[5,19,65],"robustness":[6],"of":[7,21,50,58,67,93],"small-footprint":[8],"keyword":[9],"spotting":[10],"models":[11],"based":[12],"on":[13],"deep":[14],"neural":[15],"networks":[16],"(DNNs)":[17],"in":[18,25,43],"presence":[20],"background":[22,71],"noise":[23],"and":[24,53,70],"far-field":[26,44],"conditions.":[27],"find":[29,75],"that":[30,63,76],"system":[31],"performance":[32],"can":[33],"be":[34],"improved":[35],"significantly,":[36],"with":[37,90],"relative":[38],"improvements":[39],"up":[40],"75%":[42],"conditions,":[45],"by":[46],"employing":[47],"a":[48,54],"combination":[49],"multi-style":[51],"training":[52],"proposed":[55],"novel":[56],"formulation":[57],"automatic":[59],"gain":[60],"control":[61],"(AGC)":[62],"estimates":[64],"levels":[66],"both":[68],"speech":[69],"noise.":[72],"Further,":[73],"we":[74],"these":[77],"allow":[79],"us":[80],"achieve":[82],"competitive":[83],"performance,":[84],"even":[85],"when":[86],"applied":[87],"DNNs":[89],"an":[91],"order":[92],"magnitude":[94],"fewer":[95],"parameters":[96],"than":[97],"our":[98],"base-line.":[99]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":21},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}