{"id":"https://openalex.org/W2167593039","doi":"https://doi.org/10.1109/icassp.2003.1202304","title":"A mismatch-aware stochastic matching algorithm for robust speech recognition","display_name":"A mismatch-aware stochastic matching algorithm for robust speech recognition","publication_year":2003,"publication_date":"2003-12-22","ids":{"openalex":"https://openalex.org/W2167593039","doi":"https://doi.org/10.1109/icassp.2003.1202304","mag":"2167593039"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1202304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202304","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5082271172","display_name":"Yuan\u2010Fu Liao","orcid":"https://orcid.org/0000-0003-0191-2178"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Fu Liao","raw_affiliation_strings":["Department of Electronic Engineering & Institute of Computer and Communication, National Taipei University of Technology, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering & Institute of Computer and Communication, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087470599","display_name":"Jeng-Shien Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jeng-Shien Lin","raw_affiliation_strings":["Department of Electronic Engineering & Institute of Computer and Communication, National Taipei University of Technology, Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering & Institute of Computer and Communication, National Taipei University of Technology, Taipei, Taiwan","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015529786","display_name":"Sin\u2010Horng Chen","orcid":"https://orcid.org/0000-0002-9820-2318"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sin-Horng Chen","raw_affiliation_strings":["Department of Communication Engineering, National Chiao Tung University, Hsinchu, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communication Engineering, National Chiao Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.28645187,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"II","last_page":"101"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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":0.7866126298904419},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.716010570526123},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5911946296691895},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5603255033493042},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5507725477218628},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5411059856414795},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5148207545280457},{"id":"https://openalex.org/keywords/gsm","display_name":"GSM","score":0.4885641038417816},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4685403108596802},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46639177203178406},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45601585507392883},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45228832960128784},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.44057056307792664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42097195982933044},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.16562777757644653},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1556585431098938},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.1485719084739685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12343430519104004}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7866126298904419},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.716010570526123},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5911946296691895},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5603255033493042},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5507725477218628},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5411059856414795},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5148207545280457},{"id":"https://openalex.org/C59201141","wikidata":"https://www.wikidata.org/wiki/Q46904","display_name":"GSM","level":2,"score":0.4885641038417816},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4685403108596802},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46639177203178406},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45601585507392883},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45228832960128784},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.44057056307792664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42097195982933044},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.16562777757644653},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1556585431098938},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.1485719084739685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12343430519104004},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2003.1202304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1202304","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"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":11,"referenced_works":["https://openalex.org/W75153181","https://openalex.org/W133802959","https://openalex.org/W1587362683","https://openalex.org/W2049633694","https://openalex.org/W2082474452","https://openalex.org/W2145051192","https://openalex.org/W2160373860","https://openalex.org/W2167152389","https://openalex.org/W6603045223","https://openalex.org/W6605458717","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W2089240210","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285","https://openalex.org/W2345063900"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,22,27,34,66],"mismatch-aware":[3],"stochastic":[4,86],"matching":[5],"(MASM)":[6],"algorithm":[7],"to":[8,33,59],"alleviate":[9],"the":[10,39,53,56,61,85],"performance":[11],"degradation":[12],"under":[13],"mismatched":[14,68],"training":[15,71],"and":[16,51,75],"testing":[17,76],"conditions.":[18],"MASM":[19,83],"first":[20],"computes":[21],"reliability":[23,57],"measure":[24,58],"of":[25,29],"applying":[26],"set":[28],"pre-trained":[30],"speech":[31,62],"models":[32],"mismatch":[35,54],"test":[36],"utterance":[37],"along":[38],"time":[40],"axis":[41],"or":[42],"among":[43],"different":[44],"feature":[45],"vector":[46],"components.":[47],"It":[48],"then":[49],"estimates":[50],"compensates":[52],"using":[55],"guide":[60],"segmentation.":[63],"Experiments":[64],"on":[65,72,77],"serious":[67],"condition":[69],"with":[70],"PSTN-speech":[73],"database":[74,80],"mobile":[78],"GSM-speech":[79],"showed":[81],"that":[82],"outperformed":[84],"match":[87],"(SM)":[88],"method,":[89],"especially,":[90],"for":[91],"short":[92],"utterances.":[93]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}