{"id":"https://openalex.org/W2963194026","doi":"https://doi.org/10.1109/iscslp.2018.8706675","title":"Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units","display_name":"Hybrid CTC-Attention based End-to-End Speech Recognition using Subword Units","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2963194026","doi":"https://doi.org/10.1109/iscslp.2018.8706675","mag":"2963194026"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5028920870","display_name":"Zhangyu Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhangyu Xiao","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010173604","display_name":"Zhijian Ou","orcid":"https://orcid.org/0000-0002-9018-5074"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhijian Ou","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101906116","display_name":"Wei Chu","orcid":"https://orcid.org/0000-0002-4595-388X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Chu","raw_affiliation_strings":["Shanghai Liulishuo Information Technology Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Shanghai Liulishuo Information Technology Co., Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029920666","display_name":"Hui Lin","orcid":"https://orcid.org/0000-0002-6559-2751"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Lin","raw_affiliation_strings":["Shanghai Liulishuo Information Technology Co., Ltd"],"affiliations":[{"raw_affiliation_string":"Shanghai Liulishuo Information Technology Co., Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5028920870"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.7463,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.94669812,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"146","last_page":"150"},"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":0.9995999932289124,"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":0.9948999881744385,"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":0.8315274715423584},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7023259401321411},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6037812232971191},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5829232931137085},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5692138671875},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5492758750915527},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5448562502861023},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.5248494148254395},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5045899152755737},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44748175144195557},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.43022847175598145},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4245247542858124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4180842638015747},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35855966806411743},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.08694809675216675}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8315274715423584},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7023259401321411},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6037812232971191},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5829232931137085},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5692138671875},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5492758750915527},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5448562502861023},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5248494148254395},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5045899152755737},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44748175144195557},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.43022847175598145},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4245247542858124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4180842638015747},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35855966806411743},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.08694809675216675},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706675","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706675","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1836465849","https://openalex.org/W2102113734","https://openalex.org/W2121879602","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2160815625","https://openalex.org/W2193413348","https://openalex.org/W2293858598","https://openalex.org/W2327501763","https://openalex.org/W2520160253","https://openalex.org/W2525778437","https://openalex.org/W2526425061","https://openalex.org/W2530486890","https://openalex.org/W2545177271","https://openalex.org/W2952288254","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963226322","https://openalex.org/W2963414781","https://openalex.org/W2963953073","https://openalex.org/W6631362777","https://openalex.org/W6638667902","https://openalex.org/W6675365184","https://openalex.org/W6687566353","https://openalex.org/W6727336983","https://openalex.org/W6728811460","https://openalex.org/W6728910023","https://openalex.org/W6734588641","https://openalex.org/W6747492260"],"related_works":["https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W2916997151","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W2949174760","https://openalex.org/W2594897229","https://openalex.org/W2151348424"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"an":[5],"end-to-end":[6],"automatic":[7],"speech":[8],"recognition":[9],"system,":[10],"which":[11],"successfully":[12],"employs":[13],"subword":[14,23,44,56],"units":[15,24,45,57],"in":[16,62],"a":[17,60,103],"hybrid":[18,80,114],"CTC-Attention":[19,81,115],"based":[20],"system.":[21,116],"The":[22,78],"are":[25],"obtained":[26],"by":[27],"the":[28,50,74,90,112],"byte-pair":[29],"encoding":[30],"(BPE)":[31],"compression":[32],"algorithm.":[33],"Compared":[34],"to":[35],"using":[36,41,55,67],"words":[37],"as":[38],"modeling":[39,63],"units,":[40],"characters":[42],"or":[43,97],"does":[46],"not":[47],"suffer":[48],"from":[49],"out-of-vocabulary":[51],"(OOV)":[52],"problem.":[53],"Furthermore,":[54],"further":[58],"offers":[59],"capability":[61],"longer":[64],"context":[65],"than":[66],"characters.":[68],"We":[69],"evaluate":[70],"different":[71],"systems":[72],"over":[73,111],"LibriSpeech":[75],"1000h":[76],"dataset.":[77],"subword-based":[79],"system":[82],"obtains":[83],"6.8%":[84],"word":[85],"error":[86],"rate":[87],"(WER)":[88],"on":[89],"test":[91],"clean":[92],"subset":[93],"without":[94],"any":[95],"dictionary":[96],"external":[98],"language":[99],"model.":[100],"This":[101],"represents":[102],"significant":[104],"improvement":[105],"(a":[106],"12.8%":[107],"WER":[108],"relative":[109],"reduction)":[110],"character-based":[113]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}