{"id":"https://openalex.org/W2000534859","doi":"https://doi.org/10.1109/icassp.2002.5743892","title":"Increasing speech recognition robustness with HMM2","display_name":"Increasing speech recognition robustness with HMM2","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2000534859","doi":"https://doi.org/10.1109/icassp.2002.5743892","mag":"2000534859"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743892","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5000851749","display_name":"Katrin Weber","orcid":"https://orcid.org/0000-0002-5821-1287"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Katrin Weber","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","EPFL-Swiss Federal Institute of Technology, Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"EPFL-Swiss Federal Institute of Technology, Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017529415","display_name":"Samy Bengio","orcid":null},"institutions":[{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Samy Bengio","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108187466","display_name":"Herv\u00e9 Bourlard","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I2614128279","display_name":"Dalle Molle Institute for Artificial Intelligence Research","ror":"https://ror.org/013355g38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I15196421","https://openalex.org/I2614128279","https://openalex.org/I57201433"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Herve Bourlard","raw_affiliation_strings":["Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","EPFL-Swiss Federal Institute of Technology, Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Dalle Molle Institute for Perceptual Artificial Intelligence, Martigny, Switzerland","institution_ids":["https://openalex.org/I2614128279"]},{"raw_affiliation_string":"EPFL-Swiss Federal Institute of Technology, Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000851749"],"corresponding_institution_ids":["https://openalex.org/I2614128279","https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13078406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"99","issue":null,"first_page":"I","last_page":"929"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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/robustness","display_name":"Robustness (evolution)","score":0.8801603317260742},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.8201687932014465},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.8142272233963013},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7521175146102905},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5636568665504456},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4624839425086975},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46219995617866516},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4471665322780609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4092532992362976},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40100613236427307},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3313967287540436},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.07890549302101135}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8801603317260742},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8201687932014465},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8142272233963013},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7521175146102905},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5636568665504456},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4624839425086975},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46219995617866516},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4471665322780609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4092532992362976},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40100613236427307},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3313967287540436},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.07890549302101135},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743892","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743892","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W204308143","https://openalex.org/W1568915220","https://openalex.org/W2135034868","https://openalex.org/W2137644217","https://openalex.org/W2145806376","https://openalex.org/W4300771300","https://openalex.org/W6603616073"],"related_works":["https://openalex.org/W2368661496","https://openalex.org/W1593591600","https://openalex.org/W2380156283","https://openalex.org/W2085241361","https://openalex.org/W2018337942","https://openalex.org/W2137133401","https://openalex.org/W2394579548","https://openalex.org/W2049648127","https://openalex.org/W2018086531","https://openalex.org/W1980297060"],"abstract_inverted_index":{"The":[0],"purpose":[1],"of":[2,10,16,69,95,107,122],"this":[3],"paper":[4],"is":[5,26,84],"to":[6,28,41,49,75,78,91],"investigate":[7],"the":[8,14,36,70,89,93,119],"behavior":[9],"HMM2":[11,25,55,71,87],"models":[12],"for":[13,59],"recognition":[15,62,127],"noisy":[17],"speech.":[18],"It":[19,83],"has":[20,88],"previously":[21],"been":[22],"shown":[23,85],"that":[24,86,103],"able":[27],"model":[29],"dynamically":[30],"important":[31],"structural":[32],"information":[33],"inherent":[34],"in":[35,52],"speech":[37,61,81,126],"signal,":[38],"often":[39],"corresponding":[40],"formant":[42,45],"positions/tracks.":[43],"As":[44],"regions":[46],"are":[47],"known":[48],"be":[50],"robust":[51],"adverse":[53],"conditions,":[54,101],"seems":[56],"particularly":[57],"promising":[58],"improving":[60],"robustness.":[63],"Here,":[64],"we":[65],"review":[66],"different":[67],"variants":[68],"approach":[72],"with":[73],"respect":[74],"their":[76],"application":[77],"noise-robust":[79],"automatic":[80,125],"recognition.":[82],"potential":[90],"tackle":[92],"problem":[94],"mismatch":[96],"between":[97],"training":[98],"and":[99,102,112],"testing":[100],"a":[104,123],"multi-stream":[105],"combination":[106],"(already":[108],"noise-robust)":[109],"cepstral":[110],"features":[111,114],"formant-like":[113],"(extracted":[115],"by":[116],"HMM2)":[117],"improves":[118],"noise":[120],"robustness":[121],"state-of-the-art":[124],"system.":[128]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
