{"id":"https://openalex.org/W2160986182","doi":"https://doi.org/10.1109/icassp.2004.1326149","title":"Combining feature compensation and weighted Viterbi decoding for noise robust speech recognition with limited adaptation data","display_name":"Combining feature compensation and weighted Viterbi decoding for noise robust speech recognition with limited adaptation data","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2160986182","doi":"https://doi.org/10.1109/icassp.2004.1326149","mag":"2160986182"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 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/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":["Department of Electrical Engineering, University of California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031104626","display_name":"A. Alwan","orcid":"https://orcid.org/0000-0002-0006-8801"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Alwan","raw_affiliation_strings":["Department of Electrical Engineering, University of California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102014291"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":0.5609,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69097185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"969"},"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/T11309","display_name":"Music and Audio Processing","score":0.9966999888420105,"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":0.7070571780204773},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6400080919265747},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6075526475906372},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.5994459986686707},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5807196497917175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5388742089271545},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5210949182510376},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5203501582145691},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.5005145072937012},{"id":"https://openalex.org/keywords/iterative-viterbi-decoding","display_name":"Iterative Viterbi decoding","score":0.49552714824676514},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3251780867576599},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.299542635679245},{"id":"https://openalex.org/keywords/sequential-decoding","display_name":"Sequential decoding","score":0.10655272006988525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7070571780204773},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6400080919265747},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6075526475906372},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.5994459986686707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5807196497917175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5388742089271545},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5210949182510376},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5203501582145691},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.5005145072937012},{"id":"https://openalex.org/C113638808","wikidata":"https://www.wikidata.org/wiki/Q6094410","display_name":"Iterative Viterbi decoding","level":5,"score":0.49552714824676514},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3251780867576599},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.299542635679245},{"id":"https://openalex.org/C193969084","wikidata":"https://www.wikidata.org/wiki/Q7452500","display_name":"Sequential decoding","level":4,"score":0.10655272006988525},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W94852177","https://openalex.org/W121116918","https://openalex.org/W172389808","https://openalex.org/W202024829","https://openalex.org/W1950777589","https://openalex.org/W2045036776","https://openalex.org/W2049633694","https://openalex.org/W2099267289","https://openalex.org/W2126109239","https://openalex.org/W2128653836","https://openalex.org/W2136466519","https://openalex.org/W2137075158","https://openalex.org/W2146871184","https://openalex.org/W3129711340","https://openalex.org/W6603839713","https://openalex.org/W6679888095"],"related_works":["https://openalex.org/W2143297499","https://openalex.org/W3096277017","https://openalex.org/W1915619113","https://openalex.org/W2790444905","https://openalex.org/W4232476001","https://openalex.org/W2133857928","https://openalex.org/W2073817053","https://openalex.org/W2136652457","https://openalex.org/W2544568790","https://openalex.org/W2783469447"],"abstract_inverted_index":{"Acoustic":[0],"models":[1,35,59,114],"trained":[2],"with":[3],"clean":[4,34,57,113],"speech":[5],"signals":[6],"suffer":[7],"in":[8,53,123],"the":[9,25,33,47,77,82,88,102,105,108,112,120,137,148],"presence":[10],"of":[11,21,24,46,69,84,98,134],"background":[12],"noise.":[13],"In":[14],"some":[15],"situations,":[16],"only":[17],"a":[18,62,66,124],"limited":[19,132],"amount":[20,83],"noisy":[22,78,85,135],"data":[23,86],"new":[26],"environment":[27],"is":[28,51,65,72],"available":[29],"based":[30],"on":[31,81,101],"which":[32,64],"could":[36,90],"be":[37,91],"adapted.":[38],"A":[39],"feature":[40,138],"compensation":[41,139],"approach":[42],"employing":[43],"polynomial":[44,67],"regression":[45,145],"signal-to-noise":[48],"ratio":[49],"(SNR)":[50],"proposed":[52],"this":[54],"paper.":[55],"While":[56],"acoustic":[58],"remain":[60],"unchanged,":[61],"bias":[63],"function":[68],"utterance":[70],"SNR":[71],"estimated":[73,116],"and":[74,111,117],"removed":[75],"from":[76],"feature.":[79],"Depending":[80],"available,":[87],"algorithm":[89,140],"flexibly":[92],"carried":[93],"out":[94],"at":[95],"different":[96],"levels":[97],"granularity.":[99],"Based":[100],"Euclidean":[103],"distance,":[104],"similarity":[106],"between":[107],"residual":[109],"distribution":[110],"are":[115],"used":[118],"as":[119],"confidence":[121],"factor":[122],"back-end":[125],"weighted":[126],"Viterbi":[127,152],"decoding":[128,153],"(WVD)":[129],"algorithm.":[130],"With":[131],"amounts":[133],"data,":[136],"outperforms":[141],"maximum":[142],"likelihood":[143],"linear":[144],"(MLLR)":[146],"for":[147],"Aurora2":[149],"database.":[150],"Weighted":[151],"further":[154],"improves":[155],"recognition":[156],"accuracy.":[157]},"counts_by_year":[{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}