{"id":"https://openalex.org/W132959719","doi":"https://doi.org/10.21437/interspeech.2004-631","title":"Weighting observation vectors for robust speech recognition in noisy environments","display_name":"Weighting observation vectors for robust speech recognition in noisy environments","publication_year":2004,"publication_date":"2004-10-04","ids":{"openalex":"https://openalex.org/W132959719","doi":"https://doi.org/10.21437/interspeech.2004-631","mag":"132959719"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2004-631","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","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/A5042119047","display_name":"Zhenyu Xiong","orcid":"https://orcid.org/0000-0001-6905-5307"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenyu Xiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101404504","display_name":"Fang Zheng","orcid":"https://orcid.org/0000-0002-9508-8687"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5082058381","display_name":"Wenhu Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhu Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2069","last_page":"2072"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"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/weighting","display_name":"Weighting","score":0.7702692747116089},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7693837881088257},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6737256050109863},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6378462910652161},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.61813884973526},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6008115410804749},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49179771542549133},{"id":"https://openalex.org/keywords/subtraction","display_name":"Subtraction","score":0.4820893108844757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44946932792663574},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43854662775993347},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23057225346565247},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15047544240951538},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11272317171096802}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7702692747116089},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7693837881088257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6737256050109863},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6378462910652161},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.61813884973526},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6008115410804749},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49179771542549133},{"id":"https://openalex.org/C68060419","wikidata":"https://www.wikidata.org/wiki/Q40754","display_name":"Subtraction","level":2,"score":0.4820893108844757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44946932792663574},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43854662775993347},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23057225346565247},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15047544240951538},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11272317171096802},{"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2004-631","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2004-631","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2004","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.539.6775","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.539.6775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://cslt.riit.tsinghua.edu.cn/~fzheng/PAPERS/2004/0410E_ICSLP_RobustASR_XZY(ZF).pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.699999988079071,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W22549796","https://openalex.org/W105750483","https://openalex.org/W2018228148","https://openalex.org/W2081656196","https://openalex.org/W2113911479","https://openalex.org/W2128653836","https://openalex.org/W2154354834","https://openalex.org/W2403203479","https://openalex.org/W3141839452"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121","https://openalex.org/W2089240210","https://openalex.org/W2131486661","https://openalex.org/W2161396743","https://openalex.org/W2386453889","https://openalex.org/W3134790285","https://openalex.org/W2345063900"],"abstract_inverted_index":{"In":[0,20],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,80],"novel":[6],"approach":[7,46,92],"to":[8,66,106],"robust":[9],"speech":[10,23,39,73],"recognition":[11],"in":[12,132],"noisy":[13],"environments":[14],"by":[15,53],"discriminating":[16],"the":[17,26,37,50,55,64,71,76,107,114,118,122,126,133],"observation":[18,27,60],"vectors.":[19],"conventional":[21,51],"HMM-based":[22],"recognition,":[24],"all":[25],"vectors":[28,61],"are":[29,84],"treated":[30],"with":[31,43,94,99],"equal":[32],"importance":[33],"no":[34],"matter":[35],"how":[36],"corresponding":[38,72],"segment":[40],"is":[41,97,129],"corrupted":[42],"noise.":[44],"Our":[45],"proposed":[47,91,119],"here":[48],"modifies":[49],"decoder":[52],"weighting":[54],"likelihood":[56],"scores":[57],"for":[58,87],"different":[59,101],"based":[62],"on":[63],"signal":[65],"noise":[67],"ratios":[68],"(SNRs)":[69],"of":[70,78,82,103,117],"frames":[74],"when":[75],"probabilities":[77],"generating":[79],"sequence":[81],"observations":[83],"being":[85],"calculated":[86],"some":[88],"models.":[89],"The":[90,110],"combined":[93],"spectral":[95,127],"subtraction":[96,128],"evaluated":[98],"four":[100],"kinds":[102],"noises":[104],"added":[105],"clean":[108],"speech.":[109],"experimental":[111],"results":[112],"show":[113],"superior":[115],"performance":[116],"method":[120,123],"over":[121],"where":[124],"only":[125],"applied,":[130],"especially":[131],"median":[134],"SNR":[135],"environments.":[136],"1.":[137]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}