{"id":"https://openalex.org/W3161022068","doi":"https://doi.org/10.1109/icassp39728.2021.9414941","title":"Partially Overlapped Inference for Long-Form Speech Recognition","display_name":"Partially Overlapped Inference for Long-Form Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3161022068","doi":"https://doi.org/10.1109/icassp39728.2021.9414941","mag":"3161022068"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/A5053295454","display_name":"Tae Gyoon Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Tae Gyoon Kang","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Samsung Electronics, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Samsung Electronics, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073103269","display_name":"Ho-Gyeong Kim","orcid":"https://orcid.org/0000-0003-1177-3853"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ho-Gyeong Kim","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Samsung Electronics, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Samsung Electronics, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005538708","display_name":"Min-Joong Lee","orcid":"https://orcid.org/0000-0003-2449-014X"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Min-Joong Lee","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Samsung Electronics, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Samsung Electronics, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413487","display_name":"Jihyun Lee","orcid":"https://orcid.org/0000-0001-7051-2587"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihyun Lee","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Samsung Electronics, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Samsung Electronics, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014777103","display_name":"Hoshik Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hoshik Lee","raw_affiliation_strings":["Samsung Advanced Institute of Technology, Samsung Electronics, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Advanced Institute of Technology, Samsung Electronics, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053295454"],"corresponding_institution_ids":["https://openalex.org/I2250650973"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77550828,"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":"5989","last_page":"5993"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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":0.9980999827384949,"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/inference","display_name":"Inference","score":0.902593195438385},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7430210709571838},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.727954626083374},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6997026801109314},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41731879115104675},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.4117850065231323},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36515533924102783},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.270592600107193}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.902593195438385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7430210709571838},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.727954626083374},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6997026801109314},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41731879115104675},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.4117850065231323},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36515533924102783},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.270592600107193}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.550000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1537327044","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2127141656","https://openalex.org/W2216056764","https://openalex.org/W2327501763","https://openalex.org/W2598392802","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2938974662","https://openalex.org/W2950913377","https://openalex.org/W2952992734","https://openalex.org/W2962824709","https://openalex.org/W2963403868","https://openalex.org/W2964272710","https://openalex.org/W2985287635","https://openalex.org/W3008181812","https://openalex.org/W3008898571","https://openalex.org/W3021984791","https://openalex.org/W3025165719","https://openalex.org/W3097777922","https://openalex.org/W3149629662","https://openalex.org/W4288333914","https://openalex.org/W4294619417","https://openalex.org/W4385245566","https://openalex.org/W6632133001","https://openalex.org/W6638749077","https://openalex.org/W6640059789","https://openalex.org/W6739901393","https://openalex.org/W6747158283","https://openalex.org/W6764416717","https://openalex.org/W6769935647","https://openalex.org/W6776544788"],"related_works":["https://openalex.org/W4226287370","https://openalex.org/W2114556850","https://openalex.org/W2159992248","https://openalex.org/W2215785064","https://openalex.org/W1625332390","https://openalex.org/W2752328056","https://openalex.org/W2951574453","https://openalex.org/W2115836268","https://openalex.org/W2770224089","https://openalex.org/W4297778748"],"abstract_inverted_index":{"While":[0],"the":[1,42,66,71,83],"end-to-end":[2],"speech":[3,34],"recognition":[4,35],"models":[5],"show":[6],"impressive":[7],"performance":[8,39,76],"on":[9,68],"many":[10],"domains,":[11],"they":[12],"have":[13],"difficulties":[14],"in":[15],"decoding":[16],"long-form":[17,33],"utterances.":[18],"The":[19],"overlapped":[20,58,85],"inference":[21,59],"algorithm":[22,73],"with":[23,77],"tie-breaking":[24],"between":[25],"two":[26],"parallel":[27],"hypotheses":[28],"has":[29],"been":[30],"proposed":[31,72],"for":[32],"and":[36],"shows":[37],"dramatic":[38],"improvements":[40],"at":[41],"expense":[43],"of":[44,57],"double":[45],"computational":[46,79],"costs.":[47],"In":[48],"this":[49],"paper,":[50],"we":[51],"propose":[52],"a":[53],"more":[54],"effective":[55],"way":[56],"by":[60],"aligning":[61],"partially":[62],"matched":[63],"hypotheses.":[64],"Through":[65],"experiment":[67],"LibriSpeech":[69],"dataset,":[70],"showed":[74],"improved":[75],"less":[78],"cost":[80],"compared":[81],"to":[82],"conventional":[84],"inference.":[86]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-25T21:42:39.735039","created_date":"2025-10-10T00:00:00"}