{"id":"https://openalex.org/W2964215376","doi":"https://doi.org/10.1109/icassp.2019.8682157","title":"Automatic Grammar Augmentation for Robust Voice Command Recognition","display_name":"Automatic Grammar Augmentation for Robust Voice Command Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2964215376","doi":"https://doi.org/10.1109/icassp.2019.8682157","mag":"2964215376"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8682157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5100397616","display_name":"Yang Yang","orcid":"https://orcid.org/0000-0002-5070-4511"},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang Yang","raw_affiliation_strings":["Qualcomm AI Research, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research, San Diego","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020991662","display_name":"Anusha Lalitha","orcid":"https://orcid.org/0000-0003-4179-7151"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anusha Lalitha","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750649","display_name":"Jinwon Lee","orcid":"https://orcid.org/0000-0003-4810-1014"},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinwon Lee","raw_affiliation_strings":["Qualcomm AI Research, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research, San Diego","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113688118","display_name":"Chris Lott","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Lott","raw_affiliation_strings":["Qualcomm AI Research, San Diego"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research, San Diego","institution_ids":["https://openalex.org/I4210087596"]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"134","issue":null,"first_page":"6376","last_page":"6380"},"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":0.9994000196456909,"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":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.803203821182251},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6614359021186829},{"id":"https://openalex.org/keywords/grammar","display_name":"Grammar","score":0.6498996019363403},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5296366214752197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5272309184074402},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5108696818351746},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.4693639576435089},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4145902991294861},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3969545364379883},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3217606842517853},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15728193521499634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.803203821182251},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6614359021186829},{"id":"https://openalex.org/C26022165","wikidata":"https://www.wikidata.org/wiki/Q8091","display_name":"Grammar","level":2,"score":0.6498996019363403},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5296366214752197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5272309184074402},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5108696818351746},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.4693639576435089},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4145902991294861},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3969545364379883},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3217606842517853},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15728193521499634},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8682157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8682157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1828163288","https://openalex.org/W1922655562","https://openalex.org/W2034940213","https://openalex.org/W2123859855","https://openalex.org/W2127141656","https://openalex.org/W2132083787","https://openalex.org/W2193413348","https://openalex.org/W2407023693","https://openalex.org/W2515801922","https://openalex.org/W2520160253","https://openalex.org/W2750499125","https://openalex.org/W2963211739","https://openalex.org/W2963827914","https://openalex.org/W6687566353","https://openalex.org/W6714171909"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W1769849273","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W50892825","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817","https://openalex.org/W2158882055"],"abstract_inverted_index":{"This":[0],"paper":[1,138],"proposes":[2],"a":[3,12,49,53,122],"novel":[4],"pipeline":[5,131],"for":[6,21,61,112],"automatic":[7],"grammar":[8,42,46,51,57,115],"augmentation":[9,62],"that":[10,71,128],"provides":[11],"significant":[13],"improvement":[14,30],"in":[15,78,86,136],"the":[16,35,73,79,129,141,148,154],"voice":[17,37],"command":[18,38],"recognition":[19,119],"accuracy":[20,120],"systems":[22],"with":[23,44,117,133],"small":[24],"footprint":[25],"acoustic":[26],"model":[27],"(AM).":[28],"The":[29],"is":[31,63],"achieved":[32],"by":[33,84],"augmenting":[34],"user-defined":[36],"set,":[39,43,52,99],"also":[40,152],"called":[41],"alternate":[45],"expressions.":[47],"For":[48],"given":[50],"set":[54,116],"of":[55,81,158],"potential":[56],"expressions":[58],"(candidate":[59],"set)":[60],"constructed":[64],"from":[65],"an":[66,113],"AM-specific":[67],"statistical":[68],"pronunciation":[69],"dictionary":[70],"captures":[72],"consistent":[74,155],"patterns":[75],"and":[76,93,103,143],"errors":[77],"decoding":[80],"AM":[82],"induced":[83],"variations":[85],"pronunciation,":[87],"pitch,":[88],"tempo,":[89],"accent,":[90],"ambiguous":[91],"spellings,":[92],"noise":[94],"conditions.":[95],"Using":[96],"this":[97,137],"candidate":[98],"greedy":[100],"optimization":[101],"based":[102,106],"cross-entropy-method":[104],"(CEM)":[105],"algorithms":[107,134],"are":[108],"considered":[109,135],"to":[110],"search":[111],"augmented":[114],"improved":[118],"utilizing":[121],"command-specific":[123],"dataset.":[124],"Our":[125],"experiments":[126],"show":[127],"proposed":[130],"along":[132],"significantly":[139],"reduce":[140],"mis-detection":[142],"mis-classification":[144],"rate":[145],"without":[146],"increasing":[147],"false-alarm":[149],"rate.":[150],"Experiments":[151],"demonstrate":[153],"superior":[156],"performance":[157],"CEM":[159],"method":[160],"over":[161],"greedy-based":[162],"algorithms.":[163]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}