{"id":"https://openalex.org/W2070823712","doi":"https://doi.org/10.1109/icassp.2009.4960487","title":"Incorporating mask modelling for noise-robust automatic speech recognition","display_name":"Incorporating mask modelling for noise-robust automatic speech recognition","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2070823712","doi":"https://doi.org/10.1109/icassp.2009.4960487","mag":"2070823712"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 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/A5012447353","display_name":"M\u00fcnevver K\u00f6k\u00fcer","orcid":"https://orcid.org/0000-0002-5164-7125"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Munevver Kokuer","raw_affiliation_strings":["School of Electronic, Electrical & Computer Engineering, University of Binningham, Birmingham, UK","School of Electronic, Electrical and Computer Engineering, University of Birmingham (UK)"],"affiliations":[{"raw_affiliation_string":"School of Electronic, Electrical & Computer Engineering, University of Binningham, Birmingham, UK","institution_ids":[]},{"raw_affiliation_string":"School of Electronic, Electrical and Computer Engineering, University of Birmingham (UK)","institution_ids":["https://openalex.org/I79619799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031388449","display_name":"Peter Jan\u010dovi\u010d","orcid":"https://orcid.org/0000-0002-8897-1762"},"institutions":[{"id":"https://openalex.org/I79619799","display_name":"University of Birmingham","ror":"https://ror.org/03angcq70","country_code":"GB","type":"education","lineage":["https://openalex.org/I79619799"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Jancovic","raw_affiliation_strings":["School of Electronic, Electrical & Computer Engineering, University of Binningham, Birmingham, UK","School of Electronic, Electrical and Computer Engineering, University of Birmingham (UK)"],"affiliations":[{"raw_affiliation_string":"School of Electronic, Electrical & Computer Engineering, University of Binningham, Birmingham, UK","institution_ids":[]},{"raw_affiliation_string":"School of Electronic, Electrical and Computer Engineering, University of Birmingham (UK)","institution_ids":["https://openalex.org/I79619799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012447353"],"corresponding_institution_ids":["https://openalex.org/I79619799"],"apc_list":null,"apc_paid":null,"fwci":0.7136,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68147755,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"3929","last_page":"3932"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.996399998664856,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8240005970001221},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7486839890480042},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.7428343892097473},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7365719676017761},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6958016753196716},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.46961408853530884},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46321186423301697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4494171738624573},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3123587369918823}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8240005970001221},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7486839890480042},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.7428343892097473},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7365719676017761},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6958016753196716},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.46961408853530884},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46321186423301697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4494171738624573},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3123587369918823},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2009.4960487","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire_cris_publications/d742ebad-e99c-41a3-9a65-d6813cafbbf2","is_oa":false,"landing_page_url":"https://research.birmingham.ac.uk/en/publications/d742ebad-e99c-41a3-9a65-d6813cafbbf2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402634","display_name":"University of Birmingham Research Portal (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Kokuer, M & Jancovic, P 2009, 'Incorporating Mask Modelling for Noise-Robust Automatic Speech Recognition', Paper presented at IEEE International Conference on Acoustics Speech and Signal Processing - ICASSP, 1/01/01 pp. 3929-3932.","raw_type":"conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W36058727","https://openalex.org/W141886903","https://openalex.org/W248645961","https://openalex.org/W1553437616","https://openalex.org/W1977112032","https://openalex.org/W2045036776","https://openalex.org/W2056999733","https://openalex.org/W2074354966","https://openalex.org/W2128653836","https://openalex.org/W2157821739","https://openalex.org/W2157852208","https://openalex.org/W2166227752","https://openalex.org/W2496074920","https://openalex.org/W4298843173","https://openalex.org/W6605786316","https://openalex.org/W6683022947","https://openalex.org/W6843943695"],"related_works":["https://openalex.org/W2136652457","https://openalex.org/W2169849734","https://openalex.org/W2116722627","https://openalex.org/W2129150969","https://openalex.org/W2236912844","https://openalex.org/W1975869217","https://openalex.org/W2401728283","https://openalex.org/W2383829109","https://openalex.org/W2379938888","https://openalex.org/W2386035178"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"investigate":[4],"an":[5,11],"incorporation":[6],"of":[7,38,90],"mask":[8,16,72],"modelling":[9,73],"into":[10],"HMM-based":[12],"ASR":[13],"system.":[14],"The":[15],"model":[17,79],"is":[18,54,74],"estimated":[19],"for":[20,48,87],"each":[21],"HMM":[22,50],"state":[23],"and":[24,33,80],"mixture":[25],"by":[26,46],"using":[27],"a":[28],"separate":[29],"Viterbi-style":[30],"training":[31],"procedure":[32],"it":[34],"expresses":[35],"which":[36],"regions":[37],"the":[39,49,61,71,77,88,91],"spectrum":[40],"are":[41,68],"expected":[42],"to":[43],"be":[44],"uncorrupted":[45],"noise":[47],"state.":[51],"Experimental":[52],"evaluation":[53],"performed":[55],"on":[56],"noisy":[57],"speech":[58],"data":[59],"from":[60],"Aurora":[62],"2":[63],"database.":[64],"Significant":[65],"performance":[66],"improvements":[67],"achieved":[69],"when":[70],"incorporated":[75],"within":[76],"standard":[78],"two":[81],"models":[82],"that":[83],"had":[84],"already":[85],"compensated":[86],"effect":[89],"noise.":[92]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}