{"id":"https://openalex.org/W2296264754","doi":"https://doi.org/10.21437/interspeech.2011-421","title":"A soft decision-based speech enhancement using acoustic noise classification","display_name":"A soft decision-based speech enhancement using acoustic noise classification","publication_year":2011,"publication_date":"2011-08-27","ids":{"openalex":"https://openalex.org/W2296264754","doi":"https://doi.org/10.21437/interspeech.2011-421","mag":"2296264754"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2011-421","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","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/A5107790775","display_name":"Jae-Hun Choi","orcid":"https://orcid.org/0009-0001-1332-3883"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jae-Hun Choi","raw_affiliation_strings":["NAVER CORPORATION"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NAVER CORPORATION","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101906274","display_name":"Sang\u2010Kyun Kim","orcid":"https://orcid.org/0000-0003-1195-9236"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sang-Kyun Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002418613","display_name":"Joon\u2010Hyuk Chang","orcid":"https://orcid.org/0000-0003-2610-2323"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Hyuk Chang","raw_affiliation_strings":[", Hanyang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":", Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"1193","last_page":"1196"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9969000220298767,"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/noise","display_name":"Noise (video)","score":0.67958664894104},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6748796701431274},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6706783771514893},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6559653282165527},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.6247466206550598},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6208450198173523},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5940394401550293},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5415011644363403},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5273017883300781},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.5035502314567566},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.47253134846687317},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46216368675231934},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.24844729900360107},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.12878453731536865}],"concepts":[{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.67958664894104},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6748796701431274},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6706783771514893},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6559653282165527},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.6247466206550598},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6208450198173523},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5940394401550293},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5415011644363403},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5273017883300781},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.5035502314567566},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.47253134846687317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46216368675231934},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.24844729900360107},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.12878453731536865},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2011-421","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2011-421","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2011","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W44176993","https://openalex.org/W109290487","https://openalex.org/W2112525593","https://openalex.org/W2121973264","https://openalex.org/W2144404214","https://openalex.org/W2153384885","https://openalex.org/W2165895664"],"related_works":["https://openalex.org/W2054007705","https://openalex.org/W2002243964","https://openalex.org/W2022538999","https://openalex.org/W3090086172","https://openalex.org/W1955763106","https://openalex.org/W2986378528","https://openalex.org/W2025188156","https://openalex.org/W3178345791","https://openalex.org/W4375869276","https://openalex.org/W1550854977"],"abstract_inverted_index":{"In":[0],"this":[1],"letter,":[2],"we":[3],"present":[4],"a":[5,78],"speech":[6,28,91],"enhancement":[7,29],"technique":[8],"based":[9],"on":[10,77],"the":[11,16,25,33,37,42,47,57,68,72,82,85,90,96,99],"ambient":[12],"noise":[13,48,73],"classification":[14,74],"incorporating":[15],"Gaussian":[17,109],"mixture":[18],"model":[19],"(GMM).":[20],"The":[21],"principal":[22],"parameters":[23],"of":[24,46,98],"statistical":[26],"model-based":[27],"algorithm":[30],"such":[31],"as":[32,52],"weighting":[34],"parameter":[35,45],"in":[36],"decision-directed":[38],"(DD)":[39],"method":[40],"and":[41,94],"long-term":[43],"smoothing":[44],"estimation,":[49],"are":[50],"chosen":[51],"different":[53],"values":[54],"according":[55],"to":[56,60],"classified":[58],"contexts":[59],"ensure":[61],"best":[62],"performance":[63],"for":[64],"each":[65],"noise.":[66],"For":[67],"real-time":[69],"environment":[70],"awareness,":[71],"is":[75],"performed":[76],"frame-by-frame":[79],"basis":[80],"using":[81],"GMM":[83],"with":[84],"soft":[86],"decision":[87],"framework.":[88],"Thespeechabsenceprobability(SAP)isusedindetecting":[89],"absence":[92],"periods":[93],"updating":[95],"likelihood":[97],"GMM.":[100],"Index":[101],"Terms:":[102],"Speech":[103],"Enhancement,":[104],"Noise":[105],"Classification,":[106],"Soft":[107],"Decision,":[108],"Mixture":[110],"Model":[111]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}