{"id":"https://openalex.org/W4372260573","doi":"https://doi.org/10.1109/icassp49357.2023.10095838","title":"A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale","display_name":"A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260573","doi":"https://doi.org/10.1109/icassp49357.2023.10095838"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095838","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5037066965","display_name":"Cal Peyser","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"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cal Peyser","raw_affiliation_strings":["New York University,Center for Data Science","Google Inc","Center for Data Science, New York University"],"affiliations":[{"raw_affiliation_string":"New York University,Center for Data Science","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["New York University,Center for Data Science","Center for Data Science, New York University"],"affiliations":[{"raw_affiliation_string":"New York University,Center for Data Science","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057911829","display_name":"Kyunghyun Cho","orcid":null},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyunghyun Cho","raw_affiliation_strings":["New York University,Center for Data Science","Center for Data Science, New York University"],"affiliations":[{"raw_affiliation_string":"New York University,Center for Data Science","institution_ids":["https://openalex.org/I57206974"]},{"raw_affiliation_string":"Center for Data Science, New York University","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","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"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100667045","display_name":"Wei Huang","orcid":"https://orcid.org/0000-0003-4170-4875"},"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":"W. Ronny Huang","raw_affiliation_strings":["Google Inc"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Google Inc","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5037066965"],"corresponding_institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I57206974"],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63049522,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.9966999888420105,"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":0.8279218077659607},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7438514232635498},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5705734491348267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49176648259162903},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43250572681427},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4104839563369751},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39497852325439453},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3704746961593628},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.088585764169693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8279218077659607},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7438514232635498},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5705734491348267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49176648259162903},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43250572681427},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4104839563369751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39497852325439453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3704746961593628},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.088585764169693},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/icassp49357.2023.10095838","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W1993660824","https://openalex.org/W2160815625","https://openalex.org/W2327501763","https://openalex.org/W2560482944","https://openalex.org/W2888779557","https://openalex.org/W2896457183","https://openalex.org/W2963739817","https://openalex.org/W2964243274","https://openalex.org/W2972889948","https://openalex.org/W2973049979","https://openalex.org/W2979476256","https://openalex.org/W3016234571","https://openalex.org/W3036601975","https://openalex.org/W3081416955","https://openalex.org/W3095838132","https://openalex.org/W3097777922","https://openalex.org/W3163203022","https://openalex.org/W3207222250","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3212799896","https://openalex.org/W4210690962","https://openalex.org/W4221161761","https://openalex.org/W4223622550","https://openalex.org/W4226093136","https://openalex.org/W4281492411","https://openalex.org/W4319862474","https://openalex.org/W6638749077","https://openalex.org/W6730250325","https://openalex.org/W6743477263","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6780218876","https://openalex.org/W6803092890","https://openalex.org/W6803164887","https://openalex.org/W6804533152","https://openalex.org/W6810673746","https://openalex.org/W6846689237"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W4231775656","https://openalex.org/W2046435967","https://openalex.org/W2383646825","https://openalex.org/W2371018915","https://openalex.org/W2354191502","https://openalex.org/W1972225038","https://openalex.org/W4321636575","https://openalex.org/W3134658850","https://openalex.org/W2296205523"],"abstract_inverted_index":{"Unpaired":[0],"text":[1,80],"and":[2,43,52,57,63,81,121],"audio":[3,82],"injection":[4],"have":[5],"emerged":[6],"as":[7,83,85],"dominant":[8],"methods":[9,29,76,104],"for":[10,61,64],"improving":[11],"ASR":[12,33],"performance":[13],"in":[14,90,100,114],"the":[15],"absence":[16],"of":[17,87],"a":[18,48,58,91],"large":[19,40],"labeled":[20],"corpus.":[21],"However,":[22],"little":[23],"guidance":[24],"exists":[25],"on":[26,38],"deploying":[27],"these":[28,103],"to":[30],"improve":[31],"production":[32],"systems":[34],"that":[35,99],"are":[36],"trained":[37],"very":[39],"supervised":[41],"corpora":[42],"with":[44],"realistic":[45],"requirements":[46],"like":[47],"constrained":[49],"model":[50],"size":[51],"CPU":[53],"budget,":[54],"streaming":[55],"capability,":[56],"rich":[59],"lattice":[60,122],"rescoring":[62],"downstream":[65],"NLU":[66],"tasks.":[67],"In":[68],"this":[69],"work,":[70],"we":[71],"compare":[72],"three":[73],"state-of-the-art":[74],"semi-supervised":[75],"encompassing":[77],"both":[78],"unpaired":[79],"well":[84],"several":[86],"their":[88],"combinations":[89],"controlled":[92],"setting":[93,102],"using":[94],"joint":[95],"training.":[96],"We":[97],"find":[98],"our":[101],"offer":[105],"many":[106],"improvements":[107],"beyond":[108],"raw":[109],"WER,":[110,116],"including":[111],"substantial":[112],"gains":[113],"tail-word":[115],"decoder":[117],"computation":[118],"during":[119],"inference,":[120],"density.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}