{"id":"https://openalex.org/W45652944","doi":"https://doi.org/10.21437/interspeech.2005-475","title":"On integrating insights from human speech perception into automatic speech recognition","display_name":"On integrating insights from human speech perception into automatic speech recognition","publication_year":2005,"publication_date":"2005-09-04","ids":{"openalex":"https://openalex.org/W45652944","doi":"https://doi.org/10.21437/interspeech.2005-475","mag":"45652944"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2005-475","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","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/A5112247126","display_name":"Sorin Dusan","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sorin Dusan","raw_affiliation_strings":["Rutgers, University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers, University","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110218997","display_name":"L. R. Rabiner","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Larry R. Rabiner","raw_affiliation_strings":["Rutgers, University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers, University","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":3.566,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.9274682,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1233","last_page":"1236"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7610505819320679},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6703322529792786},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6686220765113831},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5611271858215332},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5079627633094788},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5041548013687134},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4411448836326599},{"id":"https://openalex.org/keywords/speech-perception","display_name":"Speech perception","score":0.43230095505714417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3427315652370453},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18693649768829346},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.0852789580821991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610505819320679},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6703322529792786},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6686220765113831},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5611271858215332},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5079627633094788},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5041548013687134},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4411448836326599},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.43230095505714417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3427315652370453},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18693649768829346},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0852789580821991},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","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":2,"locations":[{"id":"doi:10.21437/interspeech.2005-475","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2005-475","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2005","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.585.2220","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.585.2220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ece.ucsb.edu/Faculty/Rabiner/ece259/Reprints/353_dr_euro2005c.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W48303286","https://openalex.org/W120447349","https://openalex.org/W178741201","https://openalex.org/W1480485976","https://openalex.org/W1997647459","https://openalex.org/W2001496355","https://openalex.org/W2011715840","https://openalex.org/W2075295713","https://openalex.org/W2090861223","https://openalex.org/W2163680580"],"related_works":["https://openalex.org/W2028097510","https://openalex.org/W2505877856","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871"],"abstract_inverted_index":{"In":[0],"spite":[1],"of":[2,15],"the":[3,9,13,52,110,113,131],"effort":[4],"and":[5,59,85],"progress":[6],"made":[7],"during":[8],"last":[10],"few":[11],"decades,":[12],"performance":[14,44],"automatic":[16],"speech":[17,34,69,111],"recognition":[18],"(ASR)":[19],"systems":[20],"still":[21,94],"lags":[22],"far":[23],"behind":[24],"that":[25,32,48,92,126],"achieved":[26],"by":[27],"humans.":[28],"Some":[29],"researchers":[30],"think":[31,47],"more":[33],"data":[35],"will":[36],"be":[37,57,95],"sufficient":[38],"in":[39,97,121],"order":[40],"to":[41,51,56],"bridge":[42],"this":[43],"gap.":[45],"Others":[46],"radical":[49],"modifications":[50,64],"current":[53],"methods":[54],"need":[55],"made,":[58],"possible":[60],"inspirations":[61],"for":[62,104],"these":[63],"should":[65],"come":[66],"from":[67,90,109],"human":[68],"perception":[70],"(HSP).":[71],"This":[72],"paper":[73],"focuses":[74],"on":[75],"two":[76],"issues:":[77],"first,":[78],"it":[79,100],"presents":[80,101],"a":[81],"comparison":[82],"between":[83],"HSP":[84,91],"ASR":[86],"emphasizing":[87],"some":[88,102],"insights":[89],"could":[93,119],"applied":[96],"ASR;":[98],"second,":[99],"ideas":[103],"extracting":[105],"useful":[106],"non-linguistic":[107],"information":[108],"signal,":[112],"so":[114],"called":[115],"\u2018rich":[116],"transcription\u2019,":[117],"which":[118],"help":[120],"selecting":[122],"specialized":[123],"acoustic-linguistic":[124],"models":[125],"offer":[127],"higher":[128],"accuracy":[129],"than":[130],"general":[132],"models.":[133],"1.":[134]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
