{"id":"https://openalex.org/W2963881567","doi":"https://doi.org/10.1109/icassp.2017.7953242","title":"Trainable frontend for robust and far-field keyword spotting","display_name":"Trainable frontend for robust and far-field keyword spotting","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2963881567","doi":"https://doi.org/10.1109/icassp.2017.7953242","mag":"2963881567"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5100375981","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0002-3060-4345"},"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":"Yuxuan Wang","raw_affiliation_strings":["Google, Mountain View, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070314054","display_name":"Pascal Getreuer","orcid":"https://orcid.org/0000-0002-7216-3330"},"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":"Pascal Getreuer","raw_affiliation_strings":["Google, Mountain View, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061980970","display_name":"T. A. Hughes","orcid":"https://orcid.org/0000-0003-3481-0397"},"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":"Thad Hughes","raw_affiliation_strings":["Google, Mountain View, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","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, Mountain View, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","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, Mountain View, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google, Mountain View, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100375981"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":6.5373,"has_fulltext":false,"cited_by_count":118,"citation_normalized_percentile":{"value":0.97529685,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5670","last_page":"5674"},"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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":0.8783214092254639},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7686512470245361},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6623405814170837},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5573484301567078},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5387765765190125},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5096349716186523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46137532591819763},{"id":"https://openalex.org/keywords/spotting","display_name":"Spotting","score":0.42940881848335266},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4142456650733948},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3961487114429474}],"concepts":[{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.8783214092254639},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7686512470245361},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6623405814170837},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5573484301567078},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5387765765190125},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5096349716186523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46137532591819763},{"id":"https://openalex.org/C2779506182","wikidata":"https://www.wikidata.org/wiki/Q7580141","display_name":"Spotting","level":2,"score":0.42940881848335266},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4142456650733948},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3961487114429474},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953242","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953242","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1485222997","https://openalex.org/W1687555731","https://openalex.org/W2034940213","https://openalex.org/W2050693797","https://openalex.org/W2052667477","https://openalex.org/W2076105648","https://openalex.org/W2137075158","https://openalex.org/W2160815625","https://openalex.org/W2402195372","https://openalex.org/W2407023693","https://openalex.org/W2928556070","https://openalex.org/W6713401928","https://openalex.org/W6714171909"],"related_works":["https://openalex.org/W2918559346","https://openalex.org/W2114097550","https://openalex.org/W4286904253","https://openalex.org/W3119978414","https://openalex.org/W2516975559","https://openalex.org/W3206647229","https://openalex.org/W1969408022","https://openalex.org/W2000885660","https://openalex.org/W2545741539","https://openalex.org/W1989658893"],"abstract_inverted_index":{"Robust":[0],"and":[1,78,98],"far-field":[2,13,79],"speech":[3],"recognition":[4,88],"is":[5,42],"critical":[6],"to":[7,19,24,53],"enable":[8],"true":[9],"hands-free":[10],"communication.":[11],"In":[12],"conditions,":[14],"signals":[15],"are":[16],"attenuated":[17],"due":[18],"distance.":[20],"To":[21],"improve":[22],"robustness":[23],"loudness":[25],"variation,":[26],"we":[27,82,91],"introduce":[28],"a":[29],"novel":[30],"frontend":[31,113],"called":[32],"per-channel":[33],"energy":[34],"normalization":[35],"(PCEN).":[36],"The":[37,110],"key":[38],"ingredient":[39],"of":[40,45],"PCEN":[41,67,85,93,101,112],"the":[43,55,69,105],"use":[44],"an":[46],"automatic":[47],"gain":[48],"control":[49],"based":[50],"dynamic":[51],"compression":[52],"replace":[54],"widely":[56],"used":[57],"static":[58],"(such":[59],"as":[60,94],"log":[61],"or":[62,122],"root)":[63],"compression.":[64],"We":[65],"evaluate":[66],"on":[68],"keyword":[70,106],"spotting":[71,107],"task.":[72],"On":[73],"our":[74],"large":[75],"rerecorded":[76],"noisy":[77],"eval":[80],"sets,":[81],"show":[83],"that":[84],"significantly":[86],"improves":[87],"performance.":[89],"Furthermore,":[90],"model":[92,120],"neural":[95],"network":[96],"layers":[97],"optimize":[99],"high-dimensional":[100],"parameters":[102],"jointly":[103],"with":[104],"acoustic":[108],"model.":[109],"trained":[111],"demonstrates":[114],"significant":[115],"further":[116],"improvements":[117],"without":[118],"increasing":[119],"complexity":[121],"inference-time":[123],"cost.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":3}],"updated_date":"2026-06-02T09:04:35.204637","created_date":"2025-10-10T00:00:00"}
