{"id":"https://openalex.org/W3013690751","doi":"https://doi.org/10.1186/s13636-020-0170-z","title":"Segment boundary detection directed attention for online end-to-end speech recognition","display_name":"Segment boundary detection directed attention for online end-to-end speech recognition","publication_year":2020,"publication_date":"2020-01-30","ids":{"openalex":"https://openalex.org/W3013690751","doi":"https://doi.org/10.1186/s13636-020-0170-z","mag":"3013690751"},"language":"en","primary_location":{"id":"doi:10.1186/s13636-020-0170-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-020-0170-z","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-020-0170-z.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-020-0170-z.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101505189","display_name":"Junfeng Hou","orcid":"https://orcid.org/0000-0003-3635-5332"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junfeng Hou","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, 230022, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, 230022, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369085","display_name":"Wu Guo","orcid":"https://orcid.org/0000-0002-3779-7944"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu Guo","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, 230022, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, 230022, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381758","display_name":"Yan Song","orcid":"https://orcid.org/0000-0002-5668-9068"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Song","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, 230022, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, 230022, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057227915","display_name":"Li-Rong Dai","orcid":"https://orcid.org/0000-0002-0859-2827"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-Rong Dai","raw_affiliation_strings":["National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, 230022, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Laboratory for Speech and Language Information Processing, University of Science and Technology of China, Hefei, 230022, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101505189"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":2.3313,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.9055233,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2020","issue":"1","first_page":null,"last_page":null},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.7690097689628601},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6653532385826111},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.660666823387146},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5964783430099487},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.5788639187812805},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5221757888793945},{"id":"https://openalex.org/keywords/boundary","display_name":"Boundary (topology)","score":0.5001740455627441},{"id":"https://openalex.org/keywords/symbol","display_name":"Symbol (formal)","score":0.4905337691307068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4544423818588257},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.42139557003974915},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3718583285808563},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.23176833987236023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7690097689628601},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6653532385826111},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.660666823387146},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5964783430099487},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.5788639187812805},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5221757888793945},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.5001740455627441},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.4905337691307068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4544423818588257},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.42139557003974915},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3718583285808563},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.23176833987236023},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s13636-020-0170-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-020-0170-z","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-020-0170-z.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b3a603727b4349f38c534610797ae686","is_oa":true,"landing_page_url":"https://doaj.org/article/b3a603727b4349f38c534610797ae686","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing, Vol 2020, Iss 1, Pp 1-16 (2020)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13636-020-0170-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13636-020-0170-z","pdf_url":"https://asmp-eurasipjournals.springeropen.com/track/pdf/10.1186/s13636-020-0170-z.pdf","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3013690751.pdf","grobid_xml":"https://content.openalex.org/works/W3013690751.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1514535095","https://openalex.org/W1591801644","https://openalex.org/W1635512741","https://openalex.org/W1924770834","https://openalex.org/W1993411524","https://openalex.org/W2064675550","https://openalex.org/W2079735306","https://openalex.org/W2095705004","https://openalex.org/W2108677974","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2157331557","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2469312016","https://openalex.org/W2514969556","https://openalex.org/W2584265939","https://openalex.org/W2607662938","https://openalex.org/W2745439869","https://openalex.org/W2766219058","https://openalex.org/W2773781902","https://openalex.org/W2889187401","https://openalex.org/W2911445777","https://openalex.org/W2915480215","https://openalex.org/W2936123380","https://openalex.org/W2949117887","https://openalex.org/W2950300355","https://openalex.org/W2951527505","https://openalex.org/W2952726221","https://openalex.org/W2962784628","https://openalex.org/W2962799131","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963061963","https://openalex.org/W2963067130","https://openalex.org/W2963077280","https://openalex.org/W2963158258","https://openalex.org/W2963446712","https://openalex.org/W2963729263","https://openalex.org/W2963795358","https://openalex.org/W2964260331","https://openalex.org/W6600013530","https://openalex.org/W6600157343","https://openalex.org/W6600493712","https://openalex.org/W6600741150","https://openalex.org/W6604896550","https://openalex.org/W6605905859"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W3164669818","https://openalex.org/W1573546415","https://openalex.org/W2906993205","https://openalex.org/W3179968364","https://openalex.org/W2071572975","https://openalex.org/W2619993508","https://openalex.org/W2389793738","https://openalex.org/W2154037907","https://openalex.org/W2376208682"],"abstract_inverted_index":{"Abstract":[0],"Attention-based":[1],"encoder-decoder":[2],"models":[3,24,38,54],"have":[4],"recently":[5],"shown":[6],"competitive":[7],"performance":[8,202],"for":[9,25,55,95,142],"automatic":[10],"speech":[11,27,180],"recognition":[12,28,57,181],"(ASR)":[13],"compared":[14],"to":[15,21,31,62,83,135],"conventional":[16,36,102],"ASR":[17],"systems.":[18],"However,":[19],"how":[20],"employ":[22],"attention":[23,37,53,93,115,177,197],"online":[26,56,60,97,179,201],"still":[29],"needs":[30],"be":[32,183],"explored.":[33],"Different":[34],"from":[35,133],"wherein":[39],"the":[40,49,75,101,119,130,160,168,171,175],"soft":[41,122],"alignment":[42,61,98,103],"is":[43,81,127,140,149,158],"obtained":[44],"by":[45,99,166],"a":[46,84,91,138,150,156],"pass":[47],"over":[48],"entire":[50],"input":[51,66,87,144],"sequence,":[52,88],"must":[58],"learn":[59],"attend":[63],"part":[64],"of":[65,86],"sequence":[67],"monotonically":[68],"when":[69],"generating":[70],"output":[71,79,164],"symbols.":[72],"Based":[73],"on":[74,188],"fact":[76],"that":[77,194],"every":[78],"symbol":[80,165],"corresponding":[82,172],"segment":[85,120,151],"we":[89],"propose":[90],"new":[92],"mechanism":[94,198],"learning":[96],"decomposing":[100],"into":[104],"two":[105],"parts:":[106],"segmentation":[107],"\u2014segment":[108],"boundary":[109,125,152,157],"detection":[110,126],"with":[111,121,203],"hard":[112],"decision\u2014and":[113],"segment-directed":[114],"\u2014information":[116],"aggregation":[117],"within":[118,170],"attention.":[123],"The":[124,185],"conducted":[128],"along":[129],"time":[131],"axis":[132],"left":[134],"right,":[136],"and":[137,190],"decision":[139],"made":[141],"each":[143],"frame":[145],"about":[146],"whether":[147],"it":[148],"or":[153],"not.":[154],"When":[155],"detected,":[159],"decoder":[161],"generates":[162],"an":[163],"attending":[167],"inputs":[169],"segment.":[173],"With":[174],"proposed":[176,196],"mechanism,":[178],"can":[182],"realized.":[184],"experimental":[186],"results":[187],"TIMIT":[189],"WSJ":[191],"dataset":[192],"show":[193],"our":[195],"achieves":[199],"comparable":[200],"state-of-the-art":[204],"models.":[205]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}