{"id":"https://openalex.org/W2165967438","doi":"https://doi.org/10.1109/icassp.2011.5947495","title":"Speech enhancement based on log spectral envelope model and harmonicity-derived spectral mask, and its coupling with feature compensation","display_name":"Speech enhancement based on log spectral envelope model and harmonicity-derived spectral mask, and its coupling with feature compensation","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2165967438","doi":"https://doi.org/10.1109/icassp.2011.5947495","mag":"2165967438"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101618071","display_name":"Takuya Yoshioka","orcid":"https://orcid.org/0009-0003-7791-3545"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuya Yoshioka","raw_affiliation_strings":["NIT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NIT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NIT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NIT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5064","last_page":"5067"},"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/T11309","display_name":"Music and Audio Processing","score":0.9994999766349792,"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":0.9987000226974487,"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/speech-enhancement","display_name":"Speech enhancement","score":0.6993067264556885},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.6402488946914673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.614269495010376},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5899715423583984},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5733791589736938},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.5676522254943848},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5640897750854492},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4565938711166382},{"id":"https://openalex.org/keywords/harmonic","display_name":"Harmonic","score":0.44341564178466797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3925669491291046},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3715217709541321},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2742437720298767},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.21795803308486938},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09365645051002502}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6993067264556885},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.6402488946914673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.614269495010376},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5899715423583984},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5733791589736938},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.5676522254943848},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5640897750854492},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4565938711166382},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.44341564178466797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3925669491291046},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3715217709541321},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2742437720298767},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.21795803308486938},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09365645051002502},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947495","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947495","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W35070573","https://openalex.org/W59508977","https://openalex.org/W2105696145","https://openalex.org/W2128402994","https://openalex.org/W2146324387","https://openalex.org/W2159514726","https://openalex.org/W6602377038"],"related_works":["https://openalex.org/W254868496","https://openalex.org/W2073905179","https://openalex.org/W2928432034","https://openalex.org/W4200277070","https://openalex.org/W2058908861","https://openalex.org/W1989331194","https://openalex.org/W4300740495","https://openalex.org/W1969398023","https://openalex.org/W2323643941","https://openalex.org/W1998822346"],"abstract_inverted_index":{"The":[0,69,118],"use":[1,76],"of":[2,37,77,86,115],"a":[3,15,38,54,60,66,78,87,123],"speech":[4,24,55,125],"spectral":[5,62,88],"envelope":[6,63],"model":[7,64],"defined":[8],"in":[9,128],"the":[10,28,44,72,83,109],"log":[11,61,104],"spectrum-type":[12],"domain":[13],"is":[14,74,91],"common":[16],"approach":[17,33],"to":[18,71,81,112],"feature":[19,106],"enhancement":[20,56,107,126],"for":[21,93],"noise":[22,29,96,131],"robust":[23],"recognition.":[25],"However,":[26],"from":[27,43],"reduction":[30],"viewpoint,":[31],"this":[32],"ignores":[34],"non-peak":[35],"components":[36],"spectrum":[39],"and":[40,65,98],"thus":[41],"suffers":[42],"poor":[45],"SNR":[46],"improvement":[47],"during":[48],"voiced":[49],"periods.":[50],"This":[51],"paper":[52],"proposes":[53],"method":[57,73,111,121,127],"that":[58],"exploits":[59],"harmonic":[67,79],"structure.":[68],"key":[70],"its":[75],"structure":[80],"define":[82],"prior":[84],"distribution":[85],"mask,":[89],"which":[90],"used":[92],"both":[94],"accurate":[95],"estimation":[97],"attenuation.":[99],"In":[100],"addition,":[101],"we":[102],"combine":[103],"mel-frequency":[105],"with":[108],"above":[110],"take":[113],"advantage":[114],"low":[116],"dimensionality.":[117],"whole":[119],"proposed":[120],"outperforms":[122],"state-of-the-art":[124],"four":[129],"different":[130],"environments.":[132]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}