{"id":"https://openalex.org/W97769459","doi":"https://doi.org/10.21437/eurospeech.2003-548","title":"Bandwidth mismatch compensation for robust speech recognition","display_name":"Bandwidth mismatch compensation for robust speech recognition","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W97769459","doi":"https://doi.org/10.21437/eurospeech.2003-548","mag":"97769459"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-548","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/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":true,"raw_author_name":"Yuan-Fu Liao","raw_affiliation_strings":["National Taipei University of Technology"],"affiliations":[{"raw_affiliation_string":"National Taipei University of Technology","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087470599","display_name":"Jeng-Shien Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeng-Shien Lin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5020303183","display_name":"Wei-Ho Tsai","orcid":"https://orcid.org/0000-0002-0867-7951"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Ho Tsai","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082271172"],"corresponding_institution_ids":["https://openalex.org/I118292597"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.01046367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3093","last_page":"3096"},"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":0.9997000098228455,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7811852693557739},{"id":"https://openalex.org/keywords/bandwidth-extension","display_name":"Bandwidth extension","score":0.748944878578186},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7283608913421631},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.7271213531494141},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.559514045715332},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44218388199806213},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4296291768550873},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42410287261009216},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4220474660396576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4205015301704407},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.38193005323410034},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.13741281628608704},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08943530917167664}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7811852693557739},{"id":"https://openalex.org/C9387945","wikidata":"https://www.wikidata.org/wiki/Q4854770","display_name":"Bandwidth extension","level":4,"score":0.748944878578186},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7283608913421631},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.7271213531494141},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.559514045715332},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44218388199806213},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4296291768550873},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42410287261009216},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4220474660396576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4205015301704407},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.38193005323410034},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.13741281628608704},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08943530917167664}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/eurospeech.2003-548","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-548","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W75153181","https://openalex.org/W1587362683","https://openalex.org/W1603944489","https://openalex.org/W1923007241","https://openalex.org/W2135567392","https://openalex.org/W2147152002"],"related_works":["https://openalex.org/W2011561032","https://openalex.org/W2496295964","https://openalex.org/W1546240199","https://openalex.org/W1976952689","https://openalex.org/W2336887028","https://openalex.org/W1999397223","https://openalex.org/W642007152","https://openalex.org/W2056066842","https://openalex.org/W1578591928","https://openalex.org/W2536333783"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"an":[3],"iterative":[4],"bandwidth":[5,23,32,67,77,112,128],"mismatch":[6,68],"compensation":[7,69],"(BMC)":[8],"algorithm":[9],"is":[10,94],"proposed":[11,136],"to":[12,97],"alleviate":[13],"the":[14,28,31,38,48,76,79,100,106,132,135],"need":[15],"of":[16,30,52,78,134],"multiple":[17],"pre-trained":[18],"models":[19,63],"for":[20,65],"recognizing":[21],"different":[22],"speech.":[24],"The":[25,72,88],"BMC":[26,73],"uses":[27],"concept":[29],"extension":[33],"as":[34,36],"similar":[35],"in":[37],"speech":[39,53,81,102,107],"enhancement":[40],"approaches.":[41],"However,":[42],"it":[43],"aims":[44],"at":[45],"directly":[46],"improving":[47],"recognition":[49],"accuracy":[50],"instead":[51],"intelligence":[54],"or":[55,125],"quality":[56],"and":[57,70,104,120],"utilizes":[58],"only":[59],"recognizer\u2019s":[60],"hidden":[61],"Markov":[62],"(HMMs)":[64],"both":[66],"recognition.":[71],"first":[74],"detects":[75],"input":[80,101],"signal":[82],"based":[83],"on":[84,110,117,122],"a":[85],"divergence":[86],"measurement.":[87],"HMM/Gaussian":[89],"mixture":[90],"model":[91],"(GMM)based":[92],"method":[93],"then":[95],"used":[96],"iteratively":[98],"segment":[99],"utterance":[103],"compensates":[105],"features.":[108],"Experiments":[109],"serious":[111],"mismatched":[113],"conditions,":[114],"i.e.,":[115],"training":[116],"8":[118],"kHz":[119,124,127],"testing":[121],"4":[123],"5.5":[126],"database":[129],"have":[130],"verified":[131],"effectiveness":[133],"approach.":[137]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}