{"id":"https://openalex.org/W2303272654","doi":"https://doi.org/10.1109/iscslp.2012.6423522","title":"Noise-robust whispered speech recognition using a non-audible-murmur microphone with VTS compensation","display_name":"Noise-robust whispered speech recognition using a non-audible-murmur microphone with VTS compensation","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2303272654","doi":"https://doi.org/10.1109/iscslp.2012.6423522","mag":"2303272654"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2012.6423522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.ed.ac.uk/en/publications/41b1f948-7115-438f-b5a3-d6da311d8e36","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041026723","display_name":"Chenyu Yang","orcid":"https://orcid.org/0000-0002-5000-3408"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chen-Yu Yang","raw_affiliation_strings":["IFLYTEK Speech Laboratory, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"IFLYTEK Speech Laboratory, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079164497","display_name":"Georgina Brown","orcid":"https://orcid.org/0000-0001-7918-4823"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georgina Brown","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062516688","display_name":"Simon King","orcid":"https://orcid.org/0000-0002-2694-2843"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon King","raw_affiliation_strings":["The Centre for Speech Technology Research, University of Edinburgh, UK"],"affiliations":[{"raw_affiliation_string":"The Centre for Speech Technology Research, University of Edinburgh, UK","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041026723"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":1.7139,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.88248907,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"220","last_page":"223"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9976000189781189,"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":0.9901999831199646,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.8852198123931885},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7795811891555786},{"id":"https://openalex.org/keywords/noise-canceling-microphone","display_name":"Noise-canceling microphone","score":0.6325845718383789},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6186938285827637},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6012890338897705},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.48921918869018555},{"id":"https://openalex.org/keywords/compensation","display_name":"Compensation (psychology)","score":0.4862293303012848},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4646432399749756},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.4452310800552368},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4315418601036072},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43059295415878296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26016584038734436},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11797142028808594},{"id":"https://openalex.org/keywords/sound-pressure","display_name":"Sound pressure","score":0.08139201998710632},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.05546015501022339},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.055406659841537476}],"concepts":[{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.8852198123931885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7795811891555786},{"id":"https://openalex.org/C36922181","wikidata":"https://www.wikidata.org/wiki/Q7047650","display_name":"Noise-canceling microphone","level":5,"score":0.6325845718383789},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6186938285827637},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6012890338897705},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.48921918869018555},{"id":"https://openalex.org/C2780023022","wikidata":"https://www.wikidata.org/wiki/Q1338171","display_name":"Compensation (psychology)","level":2,"score":0.4862293303012848},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4646432399749756},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.4452310800552368},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4315418601036072},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43059295415878296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26016584038734436},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11797142028808594},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.08139201998710632},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.05546015501022339},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.055406659841537476},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iscslp.2012.6423522","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2012.6423522","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 8th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.ed.ac.uk:openaire/41b1f948-7115-438f-b5a3-d6da311d8e36","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/41b1f948-7115-438f-b5a3-d6da311d8e36","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yang, C-Y, Brown, G, Lu, L, Yamagishi, J & King, S 2012, Noise-robust whispered speech recognition using a non-audible-murmur microphone with VTS compensation. in Chinese Spoken Language Processing (ISCSLP), 2012 8th International Symposium on. Institute of Electrical and Electronics Engineers, pp. 220-223. https://doi.org/10.1109/ISCSLP.2012.6423522","raw_type":"contributionToPeriodical"},{"id":"pmh:oai:pure.ed.ac.uk:publications/41b1f948-7115-438f-b5a3-d6da311d8e36","is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.11820/41b1f948-7115-438f-b5a3-d6da311d8e36","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""}],"best_oa_location":{"id":"pmh:oai:pure.ed.ac.uk:openaire/41b1f948-7115-438f-b5a3-d6da311d8e36","is_oa":true,"landing_page_url":"https://www.research.ed.ac.uk/en/publications/41b1f948-7115-438f-b5a3-d6da311d8e36","pdf_url":null,"source":{"id":"https://openalex.org/S4406922455","display_name":"Edinburgh Research Explorer","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Yang, C-Y, Brown, G, Lu, L, Yamagishi, J & King, S 2012, Noise-robust whispered speech recognition using a non-audible-murmur microphone with VTS compensation. in Chinese Spoken Language Processing (ISCSLP), 2012 8th International Symposium on. Institute of Electrical and Electronics Engineers, pp. 220-223. https://doi.org/10.1109/ISCSLP.2012.6423522","raw_type":"contributionToPeriodical"},"sustainable_development_goals":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4055593462","display_name":null,"funder_award_id":"EP/I031022/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6082203376","display_name":null,"funder_award_id":"EP/J002526/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1542658733","https://openalex.org/W1573570773","https://openalex.org/W1631260214","https://openalex.org/W1963627370","https://openalex.org/W1991590998","https://openalex.org/W2008120082","https://openalex.org/W2095026407","https://openalex.org/W2126597753","https://openalex.org/W2145247325","https://openalex.org/W2154169084","https://openalex.org/W2160800342","https://openalex.org/W2164605313","https://openalex.org/W2280467666","https://openalex.org/W2400063444","https://openalex.org/W6632463189","https://openalex.org/W6634340323","https://openalex.org/W6636811518","https://openalex.org/W6680987829","https://openalex.org/W6695320854","https://openalex.org/W6712610176"],"related_works":["https://openalex.org/W2769861442","https://openalex.org/W1515932869","https://openalex.org/W1654949927","https://openalex.org/W1980506188","https://openalex.org/W1879255185","https://openalex.org/W2804363668","https://openalex.org/W2963983801","https://openalex.org/W2120442551","https://openalex.org/W4240587264","https://openalex.org/W2011776247"],"abstract_inverted_index":{"In":[0,72],"this":[1],"paper,":[2],"we":[3,82],"introduce":[4],"a":[5,14,18],"newly-created":[6],"corpus":[7],"of":[8,43],"whispered":[9,45],"speech":[10,46],"simultaneously":[11],"recorded":[12],"via":[13],"close-talking":[15,70],"microphone":[16,22,58],"and":[17,26,51],"non-audible":[19],"murmur":[20],"(NAM)":[21],"in":[23],"both":[24],"clean":[25,80],"noisy":[27],"conditions.":[28],"To":[29],"benchmark":[30],"the":[31,56,69,94],"corpus,":[32],"which":[33],"has":[34],"been":[35],"freely":[36],"released":[37],"recently,":[38],"experiments":[39],"on":[40,79],"automatic":[41],"recognition":[42],"continuous":[44],"were":[47],"conducted.":[48],"When":[49],"training":[50],"test":[52],"conditions":[53,74],"are":[54],"matched,":[55],"NAM":[57,95],"is":[59,90],"found":[60,83],"to":[61],"be":[62],"more":[63],"robust":[64],"against":[65],"background":[66],"noise":[67],"than":[68],"microphone.":[71],"mismatched":[73],"(noisy":[75],"data,":[76],"models":[77],"trained":[78],"speech),":[81],"that":[84],"Vector":[85],"Taylor":[86],"Series":[87],"(VTS)":[88],"compensation":[89],"particularly":[91],"effective":[92],"for":[93],"signal.":[96]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}