{"id":"https://openalex.org/W172389808","doi":"https://doi.org/10.21437/eurospeech.2003-510","title":"A noise-robust ASR back-end technique based on weighted viterbi recognition","display_name":"A noise-robust ASR back-end technique based on weighted viterbi recognition","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W172389808","doi":"https://doi.org/10.21437/eurospeech.2003-510","mag":"172389808"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-510","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-510","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/A5102014291","display_name":"Xiaodong Cui","orcid":"https://orcid.org/0000-0003-4865-1307"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiaodong Cui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075072276","display_name":"Alexis Bernard","orcid":"https://orcid.org/0009-0002-2834-6540"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexis Bernard","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112421995","display_name":"Abeer Alwan","orcid":"https://orcid.org/0000-0003-3390-9379"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abeer Alwan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102014291"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1714,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.77671115,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2169","last_page":"2172"},"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":0.9937999844551086,"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/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.8636101484298706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7870626449584961},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7668598294258118},{"id":"https://openalex.org/keywords/iterative-viterbi-decoding","display_name":"Iterative Viterbi decoding","score":0.7439964413642883},{"id":"https://openalex.org/keywords/soft-output-viterbi-algorithm","display_name":"Soft output Viterbi algorithm","score":0.7119877934455872},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.6954517364501953},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6663269400596619},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5573244094848633},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5075491666793823},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48947346210479736},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.47367674112319946},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.45592594146728516},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.359803169965744},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15646404027938843},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07232972979545593},{"id":"https://openalex.org/keywords/sequential-decoding","display_name":"Sequential decoding","score":0.05546310544013977}],"concepts":[{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.8636101484298706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7870626449584961},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7668598294258118},{"id":"https://openalex.org/C113638808","wikidata":"https://www.wikidata.org/wiki/Q6094410","display_name":"Iterative Viterbi decoding","level":5,"score":0.7439964413642883},{"id":"https://openalex.org/C130319729","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Soft output Viterbi algorithm","level":5,"score":0.7119877934455872},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.6954517364501953},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6663269400596619},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5573244094848633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5075491666793823},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48947346210479736},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.47367674112319946},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.45592594146728516},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.359803169965744},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15646404027938843},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07232972979545593},{"id":"https://openalex.org/C193969084","wikidata":"https://www.wikidata.org/wiki/Q7452500","display_name":"Sequential decoding","level":4,"score":0.05546310544013977},{"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:10.21437/eurospeech.2003-510","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-510","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","score":0.6499999761581421,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W94852177","https://openalex.org/W121116918","https://openalex.org/W2099267289","https://openalex.org/W2137075158","https://openalex.org/W2146871184","https://openalex.org/W2151484683","https://openalex.org/W2152827082","https://openalex.org/W2158336491"],"related_works":["https://openalex.org/W2143297499","https://openalex.org/W3096277017","https://openalex.org/W1915619113","https://openalex.org/W2544568790","https://openalex.org/W2790444905","https://openalex.org/W4232476001","https://openalex.org/W1879414379","https://openalex.org/W2783469447","https://openalex.org/W2073817053","https://openalex.org/W2146383045"],"abstract_inverted_index":{"The":[0],"performance":[1],"of":[2,28,31,66,111],"speech":[3,33,68],"recognition":[4],"systems":[5],"trained":[6,39],"in":[7,51],"quiet":[8],"degrades":[9],"signicantly":[10],"under":[11],"noisy":[12],"conditions.":[13],"To":[14],"address":[15],"this":[16,52],"problem,":[17],"a":[18,26,55,108],"Weighted":[19,85],"Viterbi":[20,77,86],"Recognition":[21,87],"(WVR)":[22],"algorithm":[23],"that":[24],"is":[25,35,59],"function":[27],"the":[29,44,62,76],"SNR":[30,73],"each":[32,67],"frame":[34,69],"proposed.":[36],"Acoustic":[37],"models":[38],"on":[40],"clean":[41],"data,":[42,113],"and":[43,96],"acoustic":[45],"front-end":[46,90],"features":[47,91],"are":[48,82],"kept":[49],"unchanged":[50],"approach.":[53],"Instead,":[54],"condence/rob":[56],"ustness":[57],"factor":[58],"assigned":[60],"to":[61,71],"output":[63],"observation":[64],"probability":[65],"according":[70],"its":[72],"estimate":[74],"during":[75],"decoding":[78],"stage.":[79],"Comparative":[80],"experiments":[81],"conducted":[83],"with":[84,88,102],"different":[89],"such":[92],"as":[93],"MFCC,":[94],"LPCC":[95],"PLP.":[97],"Results":[98],"show":[99],"consistent":[100],"improvements":[101],"all":[103],"three":[104],"feature":[105],"vectors.":[106],"For":[107],"reasonable":[109],"size":[110],"adaptation":[112,117],"WVR":[114],"outperforms":[115],"environment":[116],"using":[118],"MLLR.":[119]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}