{"id":"https://openalex.org/W2162223813","doi":"https://doi.org/10.1109/apccas.2008.4746261","title":"Analysis-by-synthesis method for whisper-speech reconstruction","display_name":"Analysis-by-synthesis method for whisper-speech reconstruction","publication_year":2008,"publication_date":"2008-11-01","ids":{"openalex":"https://openalex.org/W2162223813","doi":"https://doi.org/10.1109/apccas.2008.4746261","mag":"2162223813"},"language":"en","primary_location":{"id":"doi:10.1109/apccas.2008.4746261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas.2008.4746261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"APCCAS 2008 - 2008 IEEE Asia Pacific Conference on Circuits and Systems","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/A5064646621","display_name":"Farzaneh Ahmadi","orcid":"https://orcid.org/0000-0002-0076-0304"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Farzaneh Ahmadi","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000620878","display_name":"Ian McLoughlin","orcid":"https://orcid.org/0000-0001-7111-2008"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ian Vince McLoughlin","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019282701","display_name":"Hamid Sharifzadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hamid Reza Sharifzadeh","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5064646621"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":4.5747,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.95296965,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1280","last_page":"1283"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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":0.979200005531311,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9782000184059143,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/code-excited-linear-prediction","display_name":"Code-excited linear prediction","score":0.8307714462280273},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7820143699645996},{"id":"https://openalex.org/keywords/codec","display_name":"Codec","score":0.7045854926109314},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.6880577802658081},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.678261399269104},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.6647886037826538},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6209208965301514},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.5503196716308594},{"id":"https://openalex.org/keywords/adaptive-multi-rate-audio-codec","display_name":"Adaptive Multi-Rate audio codec","score":0.4990534782409668},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4855506122112274},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4615137577056885},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44770199060440063},{"id":"https://openalex.org/keywords/vector-sum-excited-linear-prediction","display_name":"Vector sum excited linear prediction","score":0.44257861375808716},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.42667290568351746},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.41506093740463257},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1778256595134735},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11939600110054016},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.08907374739646912},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.0779111385345459}],"concepts":[{"id":"https://openalex.org/C105964291","wikidata":"https://www.wikidata.org/wiki/Q856184","display_name":"Code-excited linear prediction","level":4,"score":0.8307714462280273},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820143699645996},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.7045854926109314},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.6880577802658081},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.678261399269104},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.6647886037826538},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6209208965301514},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.5503196716308594},{"id":"https://openalex.org/C177067256","wikidata":"https://www.wikidata.org/wiki/Q4676210","display_name":"Adaptive Multi-Rate audio codec","level":4,"score":0.4990534782409668},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4855506122112274},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4615137577056885},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44770199060440063},{"id":"https://openalex.org/C138807605","wikidata":"https://www.wikidata.org/wiki/Q7917845","display_name":"Vector sum excited linear prediction","level":5,"score":0.44257861375808716},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.42667290568351746},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.41506093740463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1778256595134735},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11939600110054016},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.08907374739646912},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0779111385345459}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apccas.2008.4746261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas.2008.4746261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"APCCAS 2008 - 2008 IEEE Asia Pacific Conference on Circuits and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:kar.kent.ac.uk:48770","is_oa":false,"landing_page_url":"https://kar.kent.ac.uk/48770/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196264","display_name":"Kent Academic Repository (University of Kent)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20581793","host_organization_name":"University of Kent","host_organization_lineage":["https://openalex.org/I20581793"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Book section"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W37326695","https://openalex.org/W1560904098","https://openalex.org/W1629698752","https://openalex.org/W1878540380","https://openalex.org/W1970272279","https://openalex.org/W1971284966","https://openalex.org/W2006046472","https://openalex.org/W2022047569","https://openalex.org/W2061881822","https://openalex.org/W2087335130","https://openalex.org/W2089959702","https://openalex.org/W6601540304","https://openalex.org/W6643108603","https://openalex.org/W6673030091"],"related_works":["https://openalex.org/W2135636570","https://openalex.org/W1551277881","https://openalex.org/W1542501197","https://openalex.org/W2511601861","https://openalex.org/W2151033622","https://openalex.org/W2027067793","https://openalex.org/W568589707","https://openalex.org/W1544698548","https://openalex.org/W3034644940","https://openalex.org/W1626193113"],"abstract_inverted_index":{"In":[0],"the":[1,7,61,109,116,132,135],"following":[2],"paper,":[3],"a":[4,17,29,32],"method":[5],"for":[6,37],"real-time":[8],"conversion":[9],"of":[10,31,39,74,84,115,134],"whispers":[11],"to":[12,56,68,130],"normal":[13,34],"phonated":[14,35],"speech":[15,36,59,70,121],"through":[16,60,100],"code":[18],"excited":[19],"linear":[20],"prediction":[21],"analysis-by-synthesis":[22],"codec":[23,112],"is":[24,98],"discussed.":[25],"This":[26],"approach":[27],"uses":[28],"template":[30],"speakerpsilas":[33],"extraction":[38],"excitation":[40],"parameters":[41],"such":[42,105],"as":[43],"pitch":[44,67,90],"and":[45,47,76,89,123],"gain,":[46],"then":[48],"injects":[49],"these":[50],"estimated":[51],"excitations":[52],"into":[53],"whispered":[54,69],"signal":[55],"synthesize":[57],"normal-sounding":[58],"CELP":[62,111],"codec.":[63],"Furthermore,":[64],"since":[65],"restoring":[66],"requires":[71],"some":[72],"considerations":[73],"quality":[75],"accuracy,":[77],"spectral":[78],"enhancements":[79],"are":[80,128],"required":[81],"in":[82],"terms":[83],"formant":[85],"shifting":[86,97],"(LSPs":[87],"modification)":[88],"injection":[91],"based":[92],"on":[93],"voiced/unvoiced":[94],"decision.":[95],"Spectral":[96],"accomplished":[99],"line-spectral":[101],"pair":[102],"adjustment.":[103],"Implementing":[104],"methods":[106],"by":[107],"using":[108],"popular":[110],"allows":[113],"integration":[114],"technique":[117],"with":[118],"any":[119],"modern":[120],"applications":[122],"devices.":[124],"Subjective":[125],"testing":[126],"results":[127],"presented":[129],"determine":[131],"effectiveness":[133],"technique.":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}