{"id":"https://openalex.org/W2144679390","doi":"https://doi.org/10.1109/icassp.1996.550597","title":"Environment-independent continuous speech recognition using neural networks and hidden Markov models","display_name":"Environment-independent continuous speech recognition using neural networks and hidden Markov models","publication_year":2002,"publication_date":"2002-12-24","ids":{"openalex":"https://openalex.org/W2144679390","doi":"https://doi.org/10.1109/icassp.1996.550597","mag":"2144679390"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1996.550597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1996.550597","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings","raw_type":"proceedings-article"},"type":"conference-paper","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/A5113697783","display_name":"Dong-Suk Yuk","orcid":null,"observed_orcids":[]},"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":"Dong-Suk Yuk","raw_affiliation_strings":["CAIP Center, Rutgers University, Piscataway, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAIP Center, Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109206218","display_name":"ChiWei Che","orcid":null,"observed_orcids":[]},"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":"ChiWei Che","raw_affiliation_strings":["CAIP Center, Rutgers University, Piscataway, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAIP Center, Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003776636","display_name":"Limin Jin","orcid":"https://orcid.org/0000-0001-9607-4810","observed_orcids":["https://orcid.org/0000-0001-9607-4810"]},"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":"Limin Jin","raw_affiliation_strings":["CAIP Center, Rutgers University, Piscataway, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAIP Center, Rutgers University, Piscataway, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103431069","display_name":"Qiguang Lin","orcid":null,"observed_orcids":[]},"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":"Qiguang Lin","raw_affiliation_strings":["CAIP Center, Rutgers University, Piscataway, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAIP Center, Rutgers University, Piscataway, NJ, USA","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":0.8155,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73132171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":null,"first_page":"3358","last_page":"3361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.00039999998989515007,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"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/continuous-speech-recognition","display_name":"continuous speech recognition","score":0.8080000281333923},{"id":"https://openalex.org/keywords/neural-network-compensation","display_name":"neural network compensation","score":0.9480000138282776},{"id":"https://openalex.org/keywords/hidden-markov-models","display_name":"hidden Markov models","score":0.8349999785423279},{"id":"https://openalex.org/keywords/additive-noise","display_name":"additive noise","score":0.7409999966621399},{"id":"https://openalex.org/keywords/telephone-speech","display_name":"telephone speech","score":0.8980000019073486},{"id":"https://openalex.org/keywords/training-test-mismatch","display_name":"training-test mismatch","score":0.47200000286102295}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8087124824523926},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7891201972961426},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7055728435516357},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6288707256317139},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5963718295097351},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.5035409331321716},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.481089323759079},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.47589361667633057},{"id":"https://openalex.org/C197698232","wikidata":"https://www.wikidata.org/wiki/Q2354216","display_name":"Telephone network","level":2,"score":0.4659358859062195},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4602872431278229},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.4484071731567383},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.41080498695373535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37946394085884094},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07241764664649963},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1996.550597","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1996.550597","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1514257238","https://openalex.org/W2045036776","https://openalex.org/W2048060899","https://openalex.org/W2080921589","https://openalex.org/W2101927907","https://openalex.org/W2104687512","https://openalex.org/W2154306382","https://openalex.org/W2154718887","https://openalex.org/W2240558466","https://openalex.org/W6690115018"],"related_works":["https://openalex.org/W2020464095","https://openalex.org/W4319347033","https://openalex.org/W1890431648","https://openalex.org/W1572861854","https://openalex.org/W1968776176","https://openalex.org/W1542588102","https://openalex.org/W1987001738","https://openalex.org/W2151333624","https://openalex.org/W2541680182","https://openalex.org/W2087609325"],"abstract_inverted_index":{"Environment-independent":[0],"continuous":[1],"speech":[2,11,70,87,101],"recognition":[3,121],"is":[4,43,65,76],"important":[5],"for":[6,72],"the":[7,25,47,60,113,116],"successful":[8],"development":[9],"of":[10,59,68,115,122],"recognizers":[12],"in":[13],"real":[14],"world":[15],"applications.":[16],"Linear":[17],"compensation":[18,41,63,119],"methods":[19],"do":[20],"not":[21,33],"work":[22],"well":[23],"if":[24],"mismatches":[26],"between":[27],"training;":[28],"and":[29,128],"testing":[30],"environments":[31],"are":[32,82,109],"linear.":[34],"In":[35],"this":[36],"paper,":[37],"a":[38,69,99],"neural":[39,61,80,117],"network":[40,62,118],"technique":[42],"explored":[44],"to":[45,84,90,93,111],"mitigate":[46],"distortion":[48],"resulting":[49],"from":[50],"additive":[51,123],"noise,":[52],"distant-talking,":[53],"or":[54],"telephone":[55,129],"channels.":[56],"The":[57],"advantage":[58],"method":[64],"that":[66],"retraining":[67],"recognizer":[71,102],"each":[73],"particular":[74],"application":[75],"avoided.":[77],"Furthermore,":[78],"since":[79],"networks":[81],"trained":[83,103],"transform":[85],"distorted":[86,105],"feature":[88],"vectors":[89],"those":[91],"corresponding":[92],"clean":[94],"speech,":[95,125,127],"it":[96],"may":[97],"outperform":[98],"retrained":[100],"on":[104],"speech.":[106,130],"Three":[107],"experiments":[108],"conducted":[110],"evaluate":[112],"capability":[114],"method;":[120],"noisy":[124],"distant-talking":[126]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2025-10-10T00:00:00"}