{"id":"https://openalex.org/W2981628011","doi":"https://doi.org/10.1109/icassp40776.2020.9053324","title":"Sequence-to-Sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding","display_name":"Sequence-to-Sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2981628011","doi":"https://doi.org/10.1109/icassp40776.2020.9053324","mag":"2981628011"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1910.12740","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039767083","display_name":"Alexander H. Liu","orcid":"https://orcid.org/0000-0003-1628-0855"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Alexander H. Liu","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University","[National Taiwan University,College of Electrical Engineering and Computer Science]"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University,College of Electrical Engineering and Computer Science]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047850191","display_name":"Tzu-Wei Sung","orcid":null},"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":"Tzu-Wei Sung","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, San Diego","University of California, Department of Computer Science and Engineering, San Diego"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, San Diego","institution_ids":["https://openalex.org/I36258959"]},{"raw_affiliation_string":"University of California, Department of Computer Science and Engineering, San Diego","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028930617","display_name":"Shun-Po Chuang","orcid":"https://orcid.org/0000-0003-0720-2732"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shun-Po Chuang","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University","[National Taiwan University,College of Electrical Engineering and Computer Science]"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University,College of Electrical Engineering and Computer Science]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University","[National Taiwan University,College of Electrical Engineering and Computer Science]"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"[National Taiwan University,College of Electrical Engineering and Computer Science]","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044010123","display_name":"Lin-shan Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Lin-shan Lee","raw_affiliation_strings":["College of Electrical Engineering and Computer Science, National Taiwan University","National Taiwan University"],"affiliations":[{"raw_affiliation_string":"College of Electrical Engineering and Computer Science, National Taiwan University","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"National Taiwan University","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039767083"],"corresponding_institution_ids":["https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00768097,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":null,"first_page":"7879","last_page":"7883"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T12031","display_name":"Speech and dialogue systems","score":0.998199999332428,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7505591511726379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7022082805633545},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6906130909919739},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6631917357444763},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6385133266448975},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5808508396148682},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5278299450874329},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5249843001365662},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5172955989837646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48373129963874817},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.44692254066467285},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4339821934700012},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.42675644159317017},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4167071580886841},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3605884313583374},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3555954694747925},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.259637713432312},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1969059705734253},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.058851391077041626}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7505591511726379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7022082805633545},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6906130909919739},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6631917357444763},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6385133266448975},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5808508396148682},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5278299450874329},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5249843001365662},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5172955989837646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48373129963874817},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.44692254066467285},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4339821934700012},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.42675644159317017},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4167071580886841},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3605884313583374},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3555954694747925},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.259637713432312},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1969059705734253},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.058851391077041626},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053324","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053324","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1910.12740","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.12740","pdf_url":"https://arxiv.org/pdf/1910.12740","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1910.12740","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1910.12740","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/0q22-rj20","is_oa":true,"landing_page_url":"https://doi.org/10.17023/0q22-rj20","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:2981628011","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1910.12740","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1910.12740","pdf_url":"https://arxiv.org/pdf/1910.12740","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2981628011.pdf","grobid_xml":"https://content.openalex.org/works/W2981628011.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1990005915","https://openalex.org/W2127141656","https://openalex.org/W2141599568","https://openalex.org/W2143612262","https://openalex.org/W2153579005","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2577366047","https://openalex.org/W2627092829","https://openalex.org/W2883586237","https://openalex.org/W2928720664","https://openalex.org/W2950577311","https://openalex.org/W2952566282","https://openalex.org/W2962699523","https://openalex.org/W2962824709","https://openalex.org/W2963341956","https://openalex.org/W2963400424","https://openalex.org/W2972889948","https://openalex.org/W2979826702","https://openalex.org/W6607333740","https://openalex.org/W6623517193","https://openalex.org/W6636510571","https://openalex.org/W6680890276","https://openalex.org/W6682691769","https://openalex.org/W6687566353","https://openalex.org/W6723250868","https://openalex.org/W6728030952","https://openalex.org/W6743440867","https://openalex.org/W6755207826","https://openalex.org/W6761602501","https://openalex.org/W6769243733","https://openalex.org/W6903921188"],"related_works":["https://openalex.org/W3016240723","https://openalex.org/W2899069432","https://openalex.org/W2415537144","https://openalex.org/W2027376919","https://openalex.org/W1958409774","https://openalex.org/W2004593519","https://openalex.org/W1866234974","https://openalex.org/W1994536225","https://openalex.org/W2400390095","https://openalex.org/W2136015992","https://openalex.org/W1849603325","https://openalex.org/W2004719753","https://openalex.org/W2169941844","https://openalex.org/W2960030954","https://openalex.org/W1571246086","https://openalex.org/W2112588130","https://openalex.org/W2336585117","https://openalex.org/W2149187660","https://openalex.org/W2066378046","https://openalex.org/W2118521812"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,48],"investigate":[4],"the":[5,14,24,30,39,45,51,57,61,68,72,83,107],"benefit":[6],"that":[7,92],"off-the-shelf":[8],"word":[9,25,41,85,94,110],"embedding":[10,26,95,111],"can":[11,96],"bring":[12],"to":[13,59,79,82],"sequence-to-sequence":[15],"(seq-to-seq)":[16],"automatic":[17],"speech":[18],"recognition":[19,100],"(ASR).":[20],"We":[21],"first":[22],"introduced":[23],"regularization":[27],"by":[28,66,71],"maximizing":[29],"cosine":[31],"similarity":[32],"between":[33],"a":[34,103],"transformed":[35,73],"decoder":[36,58,74],"feature":[37],"and":[38,106,116],"target":[40,84],"embedding.":[42,86],"Based":[43],"on":[44,89],"regularized":[46],"decoder,":[47],"further":[49],"proposed":[50],"fused":[52],"decoding":[53,65],"mechanism.":[54],"This":[55],"allows":[56],"consider":[60],"semantic":[62],"consistency":[63],"during":[64],"absorbing":[67],"information":[69],"carried":[70],"feature,":[75],"which":[76],"is":[77,118],"learned":[78],"be":[80],"close":[81],"Initial":[87],"results":[88],"LibriSpeech":[90],"demonstrated":[91],"pre-trained":[93],"significantly":[97],"lower":[98],"ASR":[99],"error":[101],"with":[102],"negligible":[104],"cost,":[105],"choice":[108],"of":[109],"algorithms":[112],"among":[113],"Skip-gram,":[114],"CBOW":[115],"BERT":[117],"important.":[119]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}