{"id":"https://openalex.org/W2157976705","doi":"https://doi.org/10.1109/icassp.2006.1660064","title":"Speech Bandwidth Enhancement using State Space Speech Dynamics","display_name":"Speech Bandwidth Enhancement using State Space Speech Dynamics","publication_year":2006,"publication_date":"2006-08-02","ids":{"openalex":"https://openalex.org/W2157976705","doi":"https://doi.org/10.1109/icassp.2006.1660064","mag":"2157976705"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2006.1660064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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/A5087336679","display_name":"Sheng Yao","orcid":"https://orcid.org/0000-0002-3306-8867"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Sheng Yao","raw_affiliation_strings":["Department of Electronic Engineering, City University, Kowloon, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, City University, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013378365","display_name":"Cheung-Fat Chan","orcid":"https://orcid.org/0000-0002-8665-3971"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Cheung-Fat Chan","raw_affiliation_strings":["Department of Electronic Engineering, City University, Kowloon, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, City University, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":0.9473,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73507614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"489"},"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":0.9994999766349792,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9973999857902527,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.7811228036880493},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7105839252471924},{"id":"https://openalex.org/keywords/wideband","display_name":"Wideband","score":0.6839212775230408},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.662664532661438},{"id":"https://openalex.org/keywords/wideband-audio","display_name":"Wideband audio","score":0.5872706174850464},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5780967473983765},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.48858699202537537},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4849384129047394},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4697067439556122},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.45842471718788147},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4396651089191437},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4101821184158325},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.303973913192749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22913405299186707},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1786336600780487},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.12214362621307373},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11769598722457886},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.0873894989490509}],"concepts":[{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.7811228036880493},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7105839252471924},{"id":"https://openalex.org/C2780202535","wikidata":"https://www.wikidata.org/wiki/Q4524457","display_name":"Wideband","level":2,"score":0.6839212775230408},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.662664532661438},{"id":"https://openalex.org/C173391809","wikidata":"https://www.wikidata.org/wiki/Q2740189","display_name":"Wideband audio","level":5,"score":0.5872706174850464},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5780967473983765},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.48858699202537537},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4849384129047394},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4697067439556122},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.45842471718788147},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4396651089191437},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4101821184158325},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.303973913192749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22913405299186707},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1786336600780487},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.12214362621307373},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11769598722457886},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.0873894989490509},{"id":"https://openalex.org/C87687168","wikidata":"https://www.wikidata.org/wiki/Q173114","display_name":"Digital audio","level":4,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2006.1660064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2006.1660064","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2006 IEEE International Conference on Acoustics Speed and Signal Processing Proceedings","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":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1269046860","https://openalex.org/W1591013319","https://openalex.org/W1603944489","https://openalex.org/W2034562896","https://openalex.org/W2109466292","https://openalex.org/W2122336353","https://openalex.org/W2126495382","https://openalex.org/W2147152002","https://openalex.org/W2149011702","https://openalex.org/W6635242828","https://openalex.org/W6676519493"],"related_works":["https://openalex.org/W2017913521","https://openalex.org/W2137927185","https://openalex.org/W2101490115","https://openalex.org/W1968385191","https://openalex.org/W2639995673","https://openalex.org/W2604437490","https://openalex.org/W1578591928","https://openalex.org/W2106874932","https://openalex.org/W2145423519","https://openalex.org/W4249111231"],"abstract_inverted_index":{"Extending":[0],"narrowband":[1,44],"speech":[2,7,16,22,103,126],"(0-4":[3,60],"kHz)":[4,9,42,61,65],"to":[5,35,50,93,122,163],"wideband":[6,20,147],"(0-8":[8],"has":[10,192],"applications":[11],"in":[12,134,156],"telephone":[13],"systems":[14,18,47,170],"and":[15,62,141,151,171,191,198],"recognition":[17],"where":[19],"training":[21],"data":[23],"may":[24],"not":[25],"be":[26,97,132,164],"available.":[27],"A":[28],"couple":[29],"of":[30,86,137,158,194],"methods":[31],"have":[32],"been":[33],"proposed":[34],"retrieve":[36],"the":[37,87,101,124,135,142],"missing":[38],"high-band":[39,63,78,88],"information":[40,57,79],"(4-8":[41,64],"from":[43],"speech.":[45],"Memoryless":[46],"are":[48,67],"likely":[49],"produce":[51],"large":[52],"hissing":[53,94],"artifacts":[54],"since":[55],"mutual":[56],"between":[58],"low-band":[59],"spectra":[66],"actually":[68],"quite":[69],"low.":[70],"Generally":[71],"speaking,":[72],"bandwidth":[73,112],"extension":[74,113],"cannot":[75],"recover":[76],"original":[77],"but":[80],"good":[81],"approximates":[82],"with":[83,115,174],"less":[84,195],"over-estimation":[85],"energy,":[89],"which":[90],"usually":[91],"refers":[92],"artifact,":[95],"can":[96,131],"obtained":[98,145],"by":[99,117],"considering":[100],"neighboring":[102],"frames.":[104],"In":[105],"this":[106],"paper,":[107],"we":[108],"propose":[109],"a":[110,119],"new":[111,185],"system":[114],"memory":[116,182],"using":[118],"state-space":[120,186],"model":[121,129],"capture":[123],"long-term":[125],"dynamics.":[127],"The":[128,154,184],"parameters":[130],"trained":[133],"sense":[136],"maximum":[138],"likelihood":[139],"(ML)":[140],"enhancement":[143],"is":[144,161,172,188],"via":[146],"state":[148],"vector":[149],"estimation":[150],"Kalman":[152],"filtering.":[153],"performance":[155],"terms":[157],"spectral":[159],"distortion":[160],"shown":[162],"much":[165],"better":[166],"than":[167],"other":[168],"memoryless":[169],"comparable":[173],"early":[175],"Continuous":[176],"Density":[177],"Hidden":[178],"Markov":[179],"Model":[180],"(CDHMM)":[181],"system.":[183],"method":[187],"inherent":[189],"sequential":[190],"advantages":[193],"processing":[196],"delays":[197],"robustness":[199],"against":[200],"block":[201],"detection":[202],"errors.":[203]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}