{"id":"https://openalex.org/W2033516862","doi":"https://doi.org/10.1109/icassp.2014.6854774","title":"Exploiting the baseband phase structure of the voiced speech for speech enhancement","display_name":"Exploiting the baseband phase structure of the voiced speech for speech enhancement","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2033516862","doi":"https://doi.org/10.1109/icassp.2014.6854774","mag":"2033516862"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5019702148","display_name":"Sanjay P. Patil","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay P. Patil","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","Department of Electrical & Computer Engineering, Clemson University, Clemson, SC 29634 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Clemson University, Clemson, SC 29634 USA","institution_ids":["https://openalex.org/I8078737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034808001","display_name":"J.N. Gowdy","orcid":null},"institutions":[{"id":"https://openalex.org/I8078737","display_name":"Clemson University","ror":"https://ror.org/037s24f05","country_code":"US","type":"education","lineage":["https://openalex.org/I8078737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John N. Gowdy","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","Department of Electrical & Computer Engineering, Clemson University, Clemson, SC 29634 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Clemson University, Clemson, SC, USA","institution_ids":["https://openalex.org/I8078737"]},{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Clemson University, Clemson, SC 29634 USA","institution_ids":["https://openalex.org/I8078737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2435,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.92590901,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"3","issue":null,"first_page":"6092","last_page":"6096"},"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":0.9994000196456909,"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/pesq","display_name":"PESQ","score":0.9836601614952087},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.795376181602478},{"id":"https://openalex.org/keywords/baseband","display_name":"Baseband","score":0.6884720921516418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6538596153259277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6447398662567139},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5611211061477661},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.4609329104423523},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.32617607712745667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27582699060440063},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09210062026977539},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.06535547971725464}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9836601614952087},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.795376181602478},{"id":"https://openalex.org/C65165936","wikidata":"https://www.wikidata.org/wiki/Q575784","display_name":"Baseband","level":3,"score":0.6884720921516418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6538596153259277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6447398662567139},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5611211061477661},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.4609329104423523},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.32617607712745667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27582699060440063},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09210062026977539},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.06535547971725464},{"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:10.1109/icassp.2014.6854774","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854774","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W2091425152","https://openalex.org/W2101304342","https://openalex.org/W2119393464","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2129120544","https://openalex.org/W2144404214","https://openalex.org/W2149535104","https://openalex.org/W2158336491","https://openalex.org/W2164010719","https://openalex.org/W2169147844","https://openalex.org/W2402466562","https://openalex.org/W6683806030","https://openalex.org/W6713813118"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W3135613579","https://openalex.org/W1973895194","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W2546593254","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"Performance":[0],"of":[1,24,43,57,61,104,120,123,145,160],"traditional":[2],"speech":[3,45,64,134],"enhancement":[4],"techniques":[5],"like":[6,28],"spectral":[7,105],"subtraction":[8,106,150],"and":[9,107,115,151],"log-Minimum":[10],"Mean":[11],"Squared":[12],"Error":[13],"Short":[14],"Time":[15],"Spectral":[16,96],"Amplitude":[17],"(log-MMSE":[18],"STSA)":[19,153],"estimation":[20,38,169],"degrades":[21],"in":[22,65,82,118],"presence":[23],"highly":[25],"non-stationary":[26,93],"noises":[27],"babble":[29],"noise.":[30],"This":[31,70,86],"is":[32,73,88,110,135,170],"mainly":[33],"due":[34],"to":[35,52,75,90,154],"inaccurate":[36],"noise":[37,78,94],"during":[39],"the":[40,44,54,58,62,66,77,83,129,143,156],"voiced":[41,63,84],"segment":[42],"signal.":[46],"In":[47],"this":[48,101],"paper,":[49],"we":[50],"propose":[51],"exploit":[53],"fine":[55],"structure":[56,72],"phase":[59,71],"spectra":[60],"baseband":[67],"STFT":[68],"domain.":[69],"used":[74,89,136],"detect":[76],"dominant":[79],"frequency":[80],"bins":[81],"frames.":[85],"information":[87],"achieve":[91,155],"better":[92],"Power":[95],"Density":[97],"(PSD)":[98],"estimation.":[99,139],"Using":[100],"estimation,":[102],"performance":[103],"log-MMSE":[108,152,164],"STSA":[109,165],"improved":[111],"overall":[112,157],"by":[113],"0.3":[114],"0.2,":[116],"respectively,":[117],"terms":[119],"Perceptual":[121],"Evaluation":[122],"Speech":[124],"Quality":[125],"(PESQ)":[126],"measure":[127],"over":[128,162],"original":[130],"algorithms":[131,148],"when":[132,166],"noisy":[133],"for":[137],"pitch":[138,168],"We":[140],"also":[141],"present":[142],"combination":[144],"these":[146],"two":[147],"(spectral":[149],"PESQ":[158],"improvement":[159],"0.5":[161],"standard":[163],"accurate":[167],"available.":[171]},"counts_by_year":[{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
