{"id":"https://openalex.org/W3207595101","doi":"https://doi.org/10.1109/icassp43922.2022.9747805","title":"Word Order does not Matter for Speech Recognition","display_name":"Word Order does not Matter for Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3207595101","doi":"https://doi.org/10.1109/icassp43922.2022.9747805","mag":"3207595101"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747805","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5028944337","display_name":"Vineel Pratap","orcid":"https://orcid.org/0000-0003-3333-910X"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Vineel Pratap","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102647000","display_name":"Qiantong Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Qiantong Xu","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106542588","display_name":"Tatiana Likhomanenko","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Tatiana Likhomanenko","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041907084","display_name":"Gabriel Synnaeve","orcid":"https://orcid.org/0000-0003-1715-3356"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Gabriel Synnaeve","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053915453","display_name":"Ronan Collobert","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ronan Collobert","raw_affiliation_strings":["Facebook AI Research"],"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028944337"],"corresponding_institution_ids":["https://openalex.org/I2252078561"],"apc_list":null,"apc_paid":null,"fwci":0.6236,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.65503124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7202","last_page":"7206"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9965999722480774,"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/speech-recognition","display_name":"Speech recognition","score":0.760577917098999},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7584186792373657},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.7056050300598145},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.578446090221405},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.5690887570381165},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5630241632461548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5270932912826538},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5238133072853088},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4887216091156006},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.46120232343673706},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4309021234512329},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4253947138786316},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.3527489900588989},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3437424302101135},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31419089436531067},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11167833209037781}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.760577917098999},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7584186792373657},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.7056050300598145},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.578446090221405},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.5690887570381165},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5630241632461548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5270932912826538},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5238133072853088},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4887216091156006},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.46120232343673706},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4309021234512329},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4253947138786316},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3527489900588989},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3437424302101135},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31419089436531067},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11167833209037781},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747805","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747805","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2127141656","https://openalex.org/W2508907749","https://openalex.org/W2626778328","https://openalex.org/W2798345491","https://openalex.org/W2932675979","https://openalex.org/W2936774411","https://openalex.org/W2953190524","https://openalex.org/W2962799225","https://openalex.org/W2964001192","https://openalex.org/W2964079874","https://openalex.org/W2972706021","https://openalex.org/W2972943112","https://openalex.org/W2975381464","https://openalex.org/W2991213871","https://openalex.org/W2996159613","https://openalex.org/W3015213852","https://openalex.org/W3015522062","https://openalex.org/W3026041220","https://openalex.org/W3034343705","https://openalex.org/W3036601975","https://openalex.org/W3041561163","https://openalex.org/W3043750461","https://openalex.org/W3047080628","https://openalex.org/W3093579165","https://openalex.org/W3094647783","https://openalex.org/W3095292526","https://openalex.org/W3095350795","https://openalex.org/W3096338464","https://openalex.org/W3099782249","https://openalex.org/W3139395121","https://openalex.org/W3160235762","https://openalex.org/W3162833755","https://openalex.org/W3165666670","https://openalex.org/W3169320628","https://openalex.org/W3196434891","https://openalex.org/W3197223534","https://openalex.org/W3197411683","https://openalex.org/W3198098585","https://openalex.org/W3198270883","https://openalex.org/W3198858531","https://openalex.org/W3209059054","https://openalex.org/W4287173589","https://openalex.org/W4385245566","https://openalex.org/W6739901393","https://openalex.org/W6757699909","https://openalex.org/W6768080748","https://openalex.org/W6770506093","https://openalex.org/W6779645881","https://openalex.org/W6780218876","https://openalex.org/W6781159832","https://openalex.org/W6784561584","https://openalex.org/W6784614252","https://openalex.org/W6784776607","https://openalex.org/W6795952400"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W3015584167","https://openalex.org/W3207595101"],"abstract_inverted_index":{"In":[0],"this":[1,66],"paper,":[2],"we":[3,72],"study":[4],"training":[5,27,70],"of":[6,19,24,42,91],"automatic":[7],"speech":[8],"recognition":[9],"system":[10,85],"in":[11,21],"a":[12,34,51,75],"weakly":[13],"supervised":[14,98],"setting":[15],"where":[16],"the":[17,25,40,57,62,69,97],"order":[18],"words":[20,59],"transcript":[22],"labels":[23],"audio":[26],"data":[28],"is":[29],"not":[30],"known.":[31],"We":[32],"train":[33,74],"word-level":[35],"acoustic":[36,77],"model":[37,67,78],"which":[38,93],"aggregates":[39],"distribution":[41],"all":[43],"output":[44],"frames":[45],"using":[46,79],"LogSumExp":[47],"operation":[48],"and":[49],"uses":[50],"cross-entropy":[52],"loss":[53],"to":[54],"match":[55],"with":[56,96],"ground-truth":[58],"distribution.":[60],"Using":[61],"pseudo-labels":[63],"generated":[64],"from":[65],"on":[68,88],"set,":[71],"then":[73],"letter-based":[76],"Connectionist":[80],"Temporal":[81],"Classification":[82],"loss.":[83],"Our":[84],"achieves":[86],"2.3%/4.6%":[87],"test-clean/test-other":[89],"subsets":[90],"LibriSpeech,":[92],"closely":[94],"matches":[95],"baseline's":[99],"performance.":[100]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}