{"id":"https://openalex.org/W1976876353","doi":"https://doi.org/10.1109/lsp.2013.2255125","title":"Speech Spectral Envelope Enhancement by HMM-Based Analysis/Resynthesis","display_name":"Speech Spectral Envelope Enhancement by HMM-Based Analysis/Resynthesis","publication_year":2013,"publication_date":"2013-04-16","ids":{"openalex":"https://openalex.org/W1976876353","doi":"https://doi.org/10.1109/lsp.2013.2255125","mag":"1976876353"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2013.2255125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2013.2255125","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5039532050","display_name":"Jos\u00e9 Luis Serrano Carmona","orcid":null},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"J. L. Carmona","raw_affiliation_strings":["Department of Teor\u00eda de la Se\u00f1al, Telem\u00e1tica y Comunicaciones, Universidad de Granada, Granada, Spain","Department of Teor\u00eda de la Se\u00f1al Telem\u00e1tica y Comunicaciones, Universidad de Granada, Granada, Spain#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Teor\u00eda de la Se\u00f1al, Telem\u00e1tica y Comunicaciones, Universidad de Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]},{"raw_affiliation_string":"Department of Teor\u00eda de la Se\u00f1al Telem\u00e1tica y Comunicaciones, Universidad de Granada, Granada, Spain#TAB#","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074458312","display_name":"Jon Barker","orcid":"https://orcid.org/0000-0002-1684-5660"},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"J. Barker","raw_affiliation_strings":["Department of Computer Science, University of Sheffield, Sheffield, UK","Department of Computer Science, University of Sheffield, Sheffield, United Kingdom,"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, UK","institution_ids":["https://openalex.org/I91136226"]},{"raw_affiliation_string":"Department of Computer Science, University of Sheffield, Sheffield, United Kingdom,","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024291487","display_name":"\u00c1ngel M. G\u00f3mez","orcid":"https://orcid.org/0000-0002-9995-3068"},"institutions":[{"id":"https://openalex.org/I173304897","display_name":"Universidad de Granada","ror":"https://ror.org/04njjy449","country_code":"ES","type":"education","lineage":["https://openalex.org/I173304897"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"A. M. Gomez","raw_affiliation_strings":["Department of Teor\u00eda de la Se\u00f1al, Telem\u00e1tica y Comunicaciones, Universidad de Granada, Granada, Spain","Department of Teor\u00eda de la Se\u00f1al Telem\u00e1tica y Comunicaciones, Universidad de Granada, Granada, Spain#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Teor\u00eda de la Se\u00f1al, Telem\u00e1tica y Comunicaciones, Universidad de Granada, Granada, Spain","institution_ids":["https://openalex.org/I173304897"]},{"raw_affiliation_string":"Department of Teor\u00eda de la Se\u00f1al Telem\u00e1tica y Comunicaciones, Universidad de Granada, Granada, Spain#TAB#","institution_ids":["https://openalex.org/I173304897"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067036469","display_name":"Ning Ma","orcid":"https://orcid.org/0000-0002-4112-3109"},"institutions":[{"id":"https://openalex.org/I4210140445","display_name":"MRC Institute of Hearing Research","ror":"https://ror.org/04gycm791","country_code":"GB","type":"facility","lineage":["https://openalex.org/I142263535","https://openalex.org/I4210087105","https://openalex.org/I4210140445","https://openalex.org/I90344618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ning Ma","raw_affiliation_strings":["MRC Institute of Hearing Research, Nottingham, UK","MRC Institute of Hearing Research, Nottingham, United Kingdom"],"affiliations":[{"raw_affiliation_string":"MRC Institute of Hearing Research, Nottingham, UK","institution_ids":["https://openalex.org/I4210140445"]},{"raw_affiliation_string":"MRC Institute of Hearing Research, Nottingham, United Kingdom","institution_ids":["https://openalex.org/I4210140445"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039532050"],"corresponding_institution_ids":["https://openalex.org/I173304897"],"apc_list":null,"apc_paid":null,"fwci":1.596,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82564133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"20","issue":"6","first_page":"563","last_page":"566"},"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":0.9998000264167786,"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":0.9993000030517578,"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/speech-recognition","display_name":"Speech recognition","score":0.799485445022583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7613129615783691},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.7202554941177368},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6668282151222229},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6262196898460388},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5522404909133911},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5348550081253052},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.5072300434112549},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4738374650478363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4447256326675415},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4302719533443451},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37047046422958374},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.29231902956962585}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.799485445022583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613129615783691},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.7202554941177368},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6668282151222229},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6262196898460388},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5522404909133911},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5348550081253052},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.5072300434112549},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4738374650478363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4447256326675415},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4302719533443451},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37047046422958374},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.29231902956962585},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2013.2255125","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2013.2255125","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W22889032","https://openalex.org/W1994396704","https://openalex.org/W2015143272","https://openalex.org/W2074354966","https://openalex.org/W2106603795","https://openalex.org/W2129142580","https://openalex.org/W2144404214","https://openalex.org/W2154920538","https://openalex.org/W2168348268","https://openalex.org/W6600974516"],"related_works":["https://openalex.org/W2038801705","https://openalex.org/W2688184458","https://openalex.org/W2904846757","https://openalex.org/W2120771489","https://openalex.org/W3110551121","https://openalex.org/W2619026611","https://openalex.org/W2131486661","https://openalex.org/W2616987818","https://openalex.org/W2089240210","https://openalex.org/W2164147372"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,10,25,37,54,74,82],"speech":[3,13,79,96,114],"enhancement-by-resynthesis":[4],"framework":[5],"whose":[6],"strength":[7],"lies":[8],"in":[9,50,53],"common":[11],"statistical":[12,89],"model":[14],"that":[15,109],"is":[16,28,43,57,118],"shared":[17],"by":[18,120],"the":[19,47,60,64,69],"analysis":[20,27],"and":[21,30,98],"synthesis":[22,42],"stages.":[23],"First,":[24],"spectro-temporal":[26,32],"performed":[29],"masked":[31,51],"regions":[33,52],"are":[34,91],"identified":[35],"using":[36],"noise":[38],"model.":[39],"Then,":[40],"HMM":[41],"used":[44],"to":[45,68],"reconstruct":[46],"spectral":[48,100],"envelope":[49],"manner":[55],"which":[56,87],"conditioned":[58],"on":[59],"reliable":[61],"regions,":[62],"preventing":[63],"resynthesis":[65],"from":[66,81],"regressing":[67],"training":[70],"data":[71],"mean.":[72],"As":[73],"demonstration":[75],"we":[76],"enhance":[77],"noise-corrupted":[78],"utterances":[80],"small":[83],"vocabulary":[84],"corpus":[85],"for":[86],"good":[88],"models":[90],"available.":[92],"Perceptual":[93],"evaluation":[94],"of":[95],"quality":[97],"log":[99],"distances":[101],"demonstrate":[102],"considerable":[103],"performance":[104],"improvements":[105],"over":[106],"baseline":[107],"approaches":[108],"do":[110],"not":[111],"exploit":[112],"strong":[113],"knowledge.":[115],"The":[116],"letter":[117],"accompanied":[119],"audio":[121],"examples.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}