{"id":"https://openalex.org/W2765677863","doi":"https://doi.org/10.1109/ncc.2017.8077073","title":"Mel-scale sub-band modelling for perceptually improved time-scale modification of speech and audio signals","display_name":"Mel-scale sub-band modelling for perceptually improved time-scale modification of speech and audio signals","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2765677863","doi":"https://doi.org/10.1109/ncc.2017.8077073","mag":"2765677863"},"language":"en","primary_location":{"id":"doi:10.1109/ncc.2017.8077073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2017.8077073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Twenty-third National Conference on Communications (NCC)","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/A5060073771","display_name":"Neeraj Kumar Sharma","orcid":"https://orcid.org/0000-0002-6391-7532"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neeraj Sharma","raw_affiliation_strings":["Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore-12, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore-12, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009551167","display_name":"Shreepad Potadar","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shreepad Potadar","raw_affiliation_strings":["Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore-12, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore-12, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004929413","display_name":"Srikanth Raj Chetupalli","orcid":"https://orcid.org/0000-0002-2186-5420"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Srikanth Raj Chetupalli","raw_affiliation_strings":["Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore-12, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore-12, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069425803","display_name":"T.V. Sreenivas","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"T.V. Sreenivas","raw_affiliation_strings":["Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore-12, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Communication Engineering, Indian Institute of Science, Bangalore-12, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.5606,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66632542,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"93","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983000159263611,"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":0.9970999956130981,"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/computer-science","display_name":"Computer science","score":0.7291863560676575},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6574486494064331},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6270738244056702},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.5969938039779663},{"id":"https://openalex.org/keywords/filter-bank","display_name":"Filter bank","score":0.5052610039710999},{"id":"https://openalex.org/keywords/sound-quality","display_name":"Sound quality","score":0.5037524104118347},{"id":"https://openalex.org/keywords/instantaneous-phase","display_name":"Instantaneous phase","score":0.472013920545578},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.4547731876373291},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4440983235836029},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4350038468837738},{"id":"https://openalex.org/keywords/narrowband","display_name":"Narrowband","score":0.4281895160675049},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.42297637462615967},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.41874730587005615},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4101620614528656},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.372130811214447},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.360590398311615},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2942555844783783},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.149306058883667},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.12707063555717468},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1267021894454956},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11437231302261353},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09387567639350891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7291863560676575},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6574486494064331},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6270738244056702},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.5969938039779663},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5052610039710999},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.5037524104118347},{"id":"https://openalex.org/C137798554","wikidata":"https://www.wikidata.org/wiki/Q6038852","display_name":"Instantaneous phase","level":3,"score":0.472013920545578},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.4547731876373291},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4440983235836029},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4350038468837738},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.4281895160675049},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.42297637462615967},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.41874730587005615},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4101620614528656},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.372130811214447},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.360590398311615},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2942555844783783},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.149306058883667},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.12707063555717468},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1267021894454956},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11437231302261353},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09387567639350891},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ncc.2017.8077073","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ncc.2017.8077073","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Twenty-third National Conference on Communications (NCC)","raw_type":"proceedings-article"},{"id":"pmh:oai::73303","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"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":25,"referenced_works":["https://openalex.org/W1521240943","https://openalex.org/W1561135842","https://openalex.org/W1933432892","https://openalex.org/W1979932443","https://openalex.org/W1989344925","https://openalex.org/W2031901258","https://openalex.org/W2043843997","https://openalex.org/W2045247893","https://openalex.org/W2058999546","https://openalex.org/W2103869314","https://openalex.org/W2110420312","https://openalex.org/W2116428736","https://openalex.org/W2125963092","https://openalex.org/W2131393611","https://openalex.org/W2167451142","https://openalex.org/W2168510624","https://openalex.org/W2295413924","https://openalex.org/W2556247670","https://openalex.org/W2973818247","https://openalex.org/W4235716345","https://openalex.org/W4245284779","https://openalex.org/W6631238246","https://openalex.org/W6633727632","https://openalex.org/W6682747227","https://openalex.org/W6696873690"],"related_works":["https://openalex.org/W1499296618","https://openalex.org/W2062136349","https://openalex.org/W4232277401","https://openalex.org/W1986860206","https://openalex.org/W2145944162","https://openalex.org/W654690113","https://openalex.org/W2171036255","https://openalex.org/W2040048036","https://openalex.org/W2607529793","https://openalex.org/W2010987884"],"abstract_inverted_index":{"Good":[0],"quality":[1,156,185],"time-scale":[2],"modification":[3],"(TSM)":[4],"of":[5,16,25,68,82,99,104,120,195],"speech,":[6,133],"and":[7,30,44,53,89,94,112,122,134,137,147,170],"audio":[8],"is":[9,19,107],"a":[10,83],"long":[11],"standing":[12],"challenge.":[13],"The":[14,78,117,180],"crux":[15],"the":[17,22,35,54,90,105,151,171],"challenge":[18],"to":[20,62,159],"maintain":[21],"perceptual":[23],"subtilities":[24],"temporal":[26],"variations":[27],"in":[28,114,141,157,183],"pitch":[29],"timbre":[31],"even":[32],"after":[33],"time-scaling":[34,110,126],"signal.":[36],"Widely":[37],"used":[38],"approaches,":[39,64],"such":[40,144],"as":[41,145],"phase":[42,96,164,168],"vocoder,":[43],"waveform":[45,160],"overlap-add":[46],"(OLA),":[47],"are":[48],"based":[49,177],"on":[50,132],"quasi-stationary":[51,76],"assumption":[52],"time-scaled":[55],"signals":[56],"have":[57],"perceivable":[58],"artifacts.":[59],"In":[60],"contrast":[61],"these":[63],"we":[65],"propose":[66],"application":[67],"time-varying":[69,101,196],"sinusoidal":[70],"modeling":[71],"for":[72,125],"TSM,":[73],"without":[74],"any":[75],"assumption.":[77],"proposed":[79,152,173],"model":[80],"comprises":[81],"mel-scale":[84],"nonuniform":[85],"bandwidth":[86],"filter":[87],"bank,":[88],"instantaneous":[91,95],"amplitude":[92],"(IA),":[93],"(IP)":[97],"factorization":[98],"sub-band":[100],"sinusoids.":[102],"TSM":[103,142,178,184],"signal":[106,197],"done":[108],"by":[109],"IA,":[111,121],"IP":[113,123],"each":[115],"sub-band.":[116],"lowpass":[118],"nature":[119],"allows":[124],"via":[127],"interpolation.":[128],"Formal":[129],"listening":[130],"tests":[131],"music":[135],"(solo,":[136],"polyphonic)":[138],"show":[139],"reduction":[140],"artifacts":[143],"phasiness,":[146],"transient":[148],"smearing.":[149],"Further,":[150],"approach":[153],"gives":[154],"improved":[155],"comparison":[158],"synchronous":[161],"OLA":[162],"(WSOLA),":[163],"vocoder":[165],"with":[166],"identity":[167],"locking,":[169],"recently":[172],"harmonic-percussive":[174],"separation":[175],"(HPS)":[176],"methods.":[179],"obtained":[181],"improvement":[182],"highlights":[186],"that":[187],"speech":[188],"analysis":[189],"can":[190],"benefit":[191],"from":[192],"appropriate":[193],"choice":[194],"models.":[198]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
