乐胖代购免代理版

{"id":"https://openalex.org/W4319862721","doi":"https://doi.org/10.1109/slt54892.2023.10022813","title":"Learning Mask Scalars for Improved Robust Automatic Speech Recognition","display_name":"Learning Mask Scalars for Improved Robust Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862721","doi":"https://doi.org/10.1109/slt54892.2023.10022813"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022813","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/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 LLC, U.S.A."],"affiliations":[{"raw_affiliation_string":"Google LLC, U.S.A.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101928782","display_name":"James S. Walker","orcid":"https://orcid.org/0000-0002-7184-584X"},"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":"James Walker","raw_affiliation_strings":["Google LLC, U.S.A."],"affiliations":[{"raw_affiliation_string":"Google LLC, U.S.A.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062398886","display_name":"Sankaran Panchapagesan","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":"Sankaran Panchapagesan","raw_affiliation_strings":["Google LLC, U.S.A."],"affiliations":[{"raw_affiliation_string":"Google LLC, U.S.A.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060708515","display_name":"N. T. Howard","orcid":"https://orcid.org/0000-0002-8787-6309"},"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":"Nathan Howard","raw_affiliation_strings":["Google LLC, U.S.A."],"affiliations":[{"raw_affiliation_string":"Google LLC, U.S.A.","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101503856","display_name":"Yuma Koizumi","orcid":"https://orcid.org/0000-0003-3645-6213"},"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":"Yuma Koizumi","raw_affiliation_strings":["Google LLC, U.S.A."],"affiliations":[{"raw_affiliation_string":"Google LLC, U.S.A.","institution_ids":["https://openalex.org/I1291425158"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.538,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.998274,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":92},"biblio":{"volume":null,"issue":null,"first_page":"317","last_page":"323"},"is_retracted":false,"is_paratext":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":0.9999,"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":0.9996,"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/robustness","display_name":"Robustness","score":0.7311973},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.72050655},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.59160316},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.52696043}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78756875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.749982},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7311973},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.72050655},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.59160316},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.52696043},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.5212927},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.42548192},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.41776642},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37277502},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.19546285},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022813","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1597121597","https://openalex.org/W2042141988","https://openalex.org/W2141411743","https://openalex.org/W2398042854","https://openalex.org/W2515439472","https://openalex.org/W2617258110","https://openalex.org/W2618099328","https://openalex.org/W2884797218","https://openalex.org/W2888860279","https://openalex.org/W2891997645","https://openalex.org/W2928941594","https://openalex.org/W2936774411","https://openalex.org/W2937769560","https://openalex.org/W2937998856","https://openalex.org/W2962935966","https://openalex.org/W2963122170","https://openalex.org/W3015194534","https://openalex.org/W3015312544","https://openalex.org/W3032514799","https://openalex.org/W3096032230","https://openalex.org/W3097777922","https://openalex.org/W3109196171","https://openalex.org/W3142252347","https://openalex.org/W3160766462","https://openalex.org/W3162646409","https://openalex.org/W3196660985","https://openalex.org/W3198667862","https://openalex.org/W3204696009","https://openalex.org/W3209059054","https://openalex.org/W3211278025","https://openalex.org/W4221153233","https://openalex.org/W4296068829","https://openalex.org/W4297841603"],"related_works":["https://openalex.org/W4319862721","https://openalex.org/W4293580959","https://openalex.org/W3211614993","https://openalex.org/W3002068412","https://openalex.org/W2964067718","https://openalex.org/W2405507568","https://openalex.org/W2151802380","https://openalex.org/W2098715841","https://openalex.org/W1584890139","https://openalex.org/W1506140669"],"abstract_inverted_index":{"Improving":[0],"robustness":[1],"of":[2,18,95],"streaming":[3],"automatic":[4],"speech":[5,96],"recognition":[6],"(ASR)":[7],"systems":[8],"using":[9,66],"neural":[10],"network":[11],"based":[12,30],"acoustic":[13,101],"frontends":[14],"is":[15],"challenging":[16],"because":[17],"causality":[19],"constraints":[20],"and":[21,52,79,97,100,130],"the":[22,26,83,93,108],"speech-distortions":[23],"introduced":[24],"by":[25],"frontend.":[27],"Time-frequency":[28],"masking":[29],"approaches":[31],"are":[32,49],"commonly":[33],"used,":[34],"but":[35],"they":[36],"need":[37],"additional":[38],"hyperparameters":[39],"\u2013":[40,43],"mask":[41,64],"scalars":[42,48,65],"to":[44,62,125,132],"limit":[45],"distortion.":[46],"Mask":[47],"typically":[50],"hand-tuned":[51,122],"chosen":[53],"conservatively.":[54],"In":[55],"this":[56],"work,":[57],"we":[58],"present":[59],"a":[60],"technique":[61],"predict":[63],"ASR":[67,88],"loss":[68],"in":[69,76,92,127],"an":[70],"end-to-end":[71],"fashion,":[72],"with":[73],"minimal":[74],"increase":[75],"model":[77],"size":[78],"complexity.":[80],"We":[81],"evaluate":[82],"approach":[84],"on":[85],"two":[86],"robust":[87],"tasks:":[89],"multichannel":[90],"enhancement":[91],"presence":[94],"non-speech":[98],"noise,":[99],"echo":[102],"cancellation":[103],"(AEC).":[104],"Results":[105],"show":[106],"that":[107,120],"presented":[109],"algorithm":[110],"consistently":[111],"improves":[112],"word":[113],"error":[114],"rate":[115],"(WER)":[116],"over":[117],"strong":[118],"baselines":[119],"use":[121],"hyperparameters:":[123],"up":[124,131],"16%":[126],"noisy":[128],"conditions,":[129],"7%":[133],"for":[134],"AEC.":[135]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4319862721","counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2025-01-01T20:37:18.130896","created_date":"2023-02-11"}