{"id":"https://openalex.org/W1989991735","doi":"https://doi.org/10.1109/ihci.2012.6481840","title":"A perceptually motivated stationary wavelet packet filter-bank utilizing improved spectral over-subtraction algorithm for enhancing speech in non-stationary environments","display_name":"A perceptually motivated stationary wavelet packet filter-bank utilizing improved spectral over-subtraction algorithm for enhancing speech in non-stationary environments","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W1989991735","doi":"https://doi.org/10.1109/ihci.2012.6481840","mag":"1989991735"},"language":"en","primary_location":{"id":"doi:10.1109/ihci.2012.6481840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ihci.2012.6481840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 4th International Conference on Intelligent Human Computer Interaction (IHCI)","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/A5014417296","display_name":"Navneet Upadhyay","orcid":"https://orcid.org/0000-0001-6097-1624"},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Navneet Upadhyay","raw_affiliation_strings":["Electrical & Electronics Engineering Department, Birla Institute of Technology & Science, Pilani, India","Electrical & Electronics Engineering Department, Birla Institute of Technology & Science, Pilani - 333031, India"],"affiliations":[{"raw_affiliation_string":"Electrical & Electronics Engineering Department, Birla Institute of Technology & Science, Pilani, India","institution_ids":["https://openalex.org/I74796645"]},{"raw_affiliation_string":"Electrical & Electronics Engineering Department, Birla Institute of Technology & Science, Pilani - 333031, India","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009425247","display_name":"Abhijit Karmakar","orcid":"https://orcid.org/0000-0002-4681-1998"},"institutions":[{"id":"https://openalex.org/I41763900","display_name":"Central Electronics Engineering Research Institute","ror":"https://ror.org/01hh45364","country_code":"IN","type":"facility","lineage":["https://openalex.org/I2799351866","https://openalex.org/I41763900","https://openalex.org/I4210134808","https://openalex.org/I66760702"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhijit Karmakar","raw_affiliation_strings":["Integrated Circuit Design Group, CSIR-Central Electronics Engineering Research Institute, Pilani, India","Integrated Circuit Design Group, CSIR-Central Electronics Engineering Research Institute, Pilani-333031, India"],"affiliations":[{"raw_affiliation_string":"Integrated Circuit Design Group, CSIR-Central Electronics Engineering Research Institute, Pilani, India","institution_ids":["https://openalex.org/I41763900"]},{"raw_affiliation_string":"Integrated Circuit Design Group, CSIR-Central Electronics Engineering Research Institute, Pilani-333031, India","institution_ids":["https://openalex.org/I41763900"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5014417296"],"corresponding_institution_ids":["https://openalex.org/I74796645"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0729622,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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":0.9995999932289124,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7364938855171204},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6557683944702148},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6048571467399597},{"id":"https://openalex.org/keywords/smoothing","display_name":"Smoothing","score":0.530059278011322},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5184942483901978},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.48657476902008057},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.47698265314102173},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46523040533065796},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.4483071565628052},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4147435128688812},{"id":"https://openalex.org/keywords/wavelet-packet-decomposition","display_name":"Wavelet packet decomposition","score":0.414356529712677},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.39125579595565796},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.38938915729522705},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3819566071033478},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.2928709387779236},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24229595065116882},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11673134565353394},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.09316444396972656},{"id":"https://openalex.org/keywords/amplifier","display_name":"Amplifier","score":0.0783662497997284},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0731610357761383}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7364938855171204},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557683944702148},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6048571467399597},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.530059278011322},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5184942483901978},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.48657476902008057},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.47698265314102173},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46523040533065796},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.4483071565628052},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4147435128688812},{"id":"https://openalex.org/C155777637","wikidata":"https://www.wikidata.org/wiki/Q2736187","display_name":"Wavelet packet decomposition","level":4,"score":0.414356529712677},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.39125579595565796},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.38938915729522705},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3819566071033478},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.2928709387779236},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24229595065116882},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11673134565353394},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.09316444396972656},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0783662497997284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0731610357761383},{"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/ihci.2012.6481840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ihci.2012.6481840","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 4th International Conference on Intelligent Human Computer Interaction (IHCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8199999928474426,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W72012584","https://openalex.org/W154898858","https://openalex.org/W228380312","https://openalex.org/W1658679052","https://openalex.org/W1968939597","https://openalex.org/W1992468098","https://openalex.org/W1997781664","https://openalex.org/W2051057783","https://openalex.org/W2109349638","https://openalex.org/W2120253085","https://openalex.org/W2126876931","https://openalex.org/W2126942983","https://openalex.org/W2128653836","https://openalex.org/W2132984323","https://openalex.org/W2146324387","https://openalex.org/W2146842127","https://openalex.org/W2149535104","https://openalex.org/W2153820018","https://openalex.org/W2158185319","https://openalex.org/W2158336491","https://openalex.org/W2485688913","https://openalex.org/W4302573160","https://openalex.org/W6602981919","https://openalex.org/W6606211187","https://openalex.org/W6840863869"],"related_works":["https://openalex.org/W3211091508","https://openalex.org/W1976952689","https://openalex.org/W2070982348","https://openalex.org/W1984921740","https://openalex.org/W2496295964","https://openalex.org/W1572861854","https://openalex.org/W2539491809","https://openalex.org/W2336887028","https://openalex.org/W2020464095","https://openalex.org/W823775484"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,9,25,107,146],"novel":[4],"speech":[5,43,86,99,124,159,182,192],"enhancement":[6,160,183],"approach":[7],"for":[8],"single-microphone":[10],"system":[11,23,161,184],"to":[12,40,66,81,96,112,205],"meet":[13],"the":[14,42,57,70,73,83,120,136,149,157,180,200],"demand":[15],"of":[16,72,98,122,148,156,187],"quality":[17],"noise":[18,49,109,114,129,189],"reduction":[19],"algorithms.":[20],"The":[21,51,76,103,127,140,154,176],"proposed":[22,158,181],"incorporates":[24],"perceptually":[26],"motivated":[27],"stationary":[28,60],"wavelet":[29,61],"packet":[30,62],"filter-bank":[31],"(PM-SWPFB)":[32],"and":[33,170,199],"improved":[34],"spectral":[35],"over-subtraction":[36],"(I-SOS)":[37],"algorithm":[38,93,105],"together":[39],"enhance":[41],"degraded":[44],"by":[45,55,133,145,165,172],"non-stationary":[46],"or":[47],"colored":[48],"environment.":[50],"PM-SWPFB":[52,77],"is":[53,94,131,143,162,185,203],"obtained":[54],"adjusting":[56],"uniformly":[58],"spaced":[59],"tree":[63],"in":[64,196],"order":[65],"most":[67],"closely":[68],"mimic":[69],"critical-bands":[71],"psycho-acoustic":[74],"model.":[75],"is,":[78],"firstly,":[79],"used":[80,95],"decompose":[82],"input":[84],"noisy":[85,137],"signal":[87,138],"into":[88],"nonuniform":[89],"sub-bands.":[90],"Then,":[91],"I-SOS":[92,104],"estimate":[97,113,130],"from":[100,116],"each":[101,117],"sub-band.":[102],"uses":[106],"new":[108],"estimation":[110],"approach,":[111],"power":[115],"sub-band":[118,128],"without":[119],"need":[121],"explicit":[123],"silence":[125],"detection.":[126],"updated":[132],"adaptively":[134],"smoothing":[135,141],"power.":[139],"parameter":[142],"controlled":[144],"function":[147],"estimated":[150],"signal-to-noise":[151],"ratio":[152],"(SNR).":[153],"performance":[155,202],"evaluated":[163],"objectively":[164],"SNR,":[166],"Itakura-Saito":[167],"distortion":[168],"measure":[169],"subjectively":[171],"informal":[173],"listening":[174],"test.":[175],"results":[177],"confirm":[178],"that":[179],"capable":[186],"reducing":[188],"with":[190],"little":[191],"degradation":[193],"remains":[194],"acceptable":[195],"real-world":[197],"environments,":[198],"overall":[201],"superior":[204],"several":[206],"competitive":[207],"methods.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}
