{"id":"https://openalex.org/W2963882470","doi":"https://doi.org/10.1109/icassp.2018.8462492","title":"Attention-Based End-to-End Speech Recognition on Voice Search","display_name":"Attention-Based End-to-End Speech Recognition on Voice Search","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2963882470","doi":"https://doi.org/10.1109/icassp.2018.8462492","mag":"2963882470"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5042775692","display_name":"Changhao Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Changhao Shan","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778479","display_name":"Junbo Zhang","orcid":"https://orcid.org/0000-0001-5947-1374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junbo Zhang","raw_affiliation_strings":["Xiaomi Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362608","display_name":"Yujun Wang","orcid":"https://orcid.org/0000-0003-2335-0946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujun Wang","raw_affiliation_strings":["Xiaomi Inc., Beijing, China"],"affiliations":[{"raw_affiliation_string":"Xiaomi Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042775692"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":6.5153,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.97310953,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4764","last_page":"4768"},"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8161097168922424},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8068608045578003},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6190075874328613},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5955005884170532},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.5390272736549377},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.535349428653717},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4895418584346771},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.46234598755836487},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.460247665643692},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.43644893169403076},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3541732430458069},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09965083003044128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8161097168922424},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8068608045578003},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6190075874328613},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5955005884170532},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.5390272736549377},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.535349428653717},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4895418584346771},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.46234598755836487},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.460247665643692},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.43644893169403076},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3541732430458069},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09965083003044128},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":0.7400000095367432,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1586532344","https://openalex.org/W1964175594","https://openalex.org/W1984541135","https://openalex.org/W2047229728","https://openalex.org/W2076063813","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2160815625","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2396384435","https://openalex.org/W2514969556","https://openalex.org/W2530876040","https://openalex.org/W2577366047","https://openalex.org/W2627092829","https://openalex.org/W2750499125","https://openalex.org/W2962826786","https://openalex.org/W2962965405","https://openalex.org/W2963211739","https://openalex.org/W6623517193","https://openalex.org/W6630875275","https://openalex.org/W6631943919","https://openalex.org/W6646550796","https://openalex.org/W6687566353","https://openalex.org/W6743440867"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W4287323699","https://openalex.org/W2105076537","https://openalex.org/W2084531783","https://openalex.org/W2050138804","https://openalex.org/W2151348424"],"abstract_inverted_index":{"Recently,":[0],"there":[1],"has":[2],"been":[3],"a":[4,37,130,138,154],"growing":[5],"interest":[6],"in":[7,117],"end-to-end":[8],"speech":[9,14,34,51],"recognition":[10,35,52],"that":[11,45],"directly":[12],"transcribes":[13],"to":[15,49,57,81,113,127],"text":[16],"without":[17],"any":[18],"predefined":[19],"alignments.":[20],"In":[21,74],"this":[22,75],"paper,":[23,76],"we":[24,77],"explore":[25],"the":[26,58,63,67,71,84,118,146],"use":[27,78,110],"of":[28,61,70,135,143],"attention-based":[29,47],"encoder-decoder":[30,48],"model":[31,93],"for":[32,91],"Mandarin":[33,50],"on":[36,145],"voice":[38,148],"search":[39,149],"task.":[40],"Previous":[41],"attempts":[42],"have":[43],"shown":[44],"applying":[46],"was":[53],"quite":[54],"difficult":[55],"due":[56],"logographic":[59],"orthography":[60],"Mandarin,":[62],"large":[64,85],"vocabulary":[65],"and":[66,101,109,137,159,163],"conditional":[68],"dependency":[69],"attention":[72,107,111,119],"model.":[73,120],"character":[79,131],"embedding":[80],"deal":[82],"with":[83,153],"vocabulary.":[86],"Several":[87],"tricks":[88,124],"are":[89],"used":[90],"effective":[92],"training,":[94],"including":[95],"L2":[96],"regularization,":[97],"Gaussian":[98],"weight":[99],"noise":[100],"frame":[102],"skipping.":[103],"We":[104],"compare":[105],"two":[106],"mechanisms":[108],"smoothing":[112],"cover":[114],"long":[115],"context":[116],"Taken":[121],"together,":[122],"these":[123],"allow":[125],"us":[126],"finally":[128],"achieve":[129],"error":[132,140],"rate":[133,141],"(CER)":[134],"3.58%":[136],"sentence":[139],"(SER)":[142],"7.43%":[144],"MiTV":[147],"dataset.":[150],"While":[151],"together":[152],"trigram":[155],"language":[156],"model,":[157],"CER":[158],"SER":[160],"reach":[161],"2.81%":[162],"5.77%,":[164],"respectively.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}