{"id":"https://openalex.org/W1492895316","doi":"https://doi.org/10.1109/icassp.1985.1168222","title":"The waveform segment vocoder: A new approach for very-low-rate speech coding","display_name":"The waveform segment vocoder: A new approach for very-low-rate speech coding","publication_year":2005,"publication_date":"2005-03-23","ids":{"openalex":"https://openalex.org/W1492895316","doi":"https://doi.org/10.1109/icassp.1985.1168222","mag":"1492895316"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1985.1168222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1985.1168222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5006694769","display_name":"S. Roucos","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"S. Roucos","raw_affiliation_strings":["Bolt Beranek and Newman,\uc2a0Inc., Cambridge, MA, USA","Bolt Beranek & Newman, Inc., Cambridge, MA"],"affiliations":[{"raw_affiliation_string":"Bolt Beranek and Newman,\uc2a0Inc., Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"Bolt Beranek & Newman, Inc., Cambridge, MA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063105052","display_name":"A. Wilgus","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"A. Wilgus","raw_affiliation_strings":["Bolt Beranek and Newman,\uc2a0Inc., Cambridge, MA, USA","[Bolt Beranek and Newman,\uc2a0Inc., Cambridge, MA, USA]"],"affiliations":[{"raw_affiliation_string":"Bolt Beranek and Newman,\uc2a0Inc., Cambridge, MA, USA","institution_ids":[]},{"raw_affiliation_string":"[Bolt Beranek and Newman,\uc2a0Inc., Cambridge, MA, USA]","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006694769"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7625,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.85211101,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"10","issue":null,"first_page":"236","last_page":"239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T11034","display_name":"Digital Filter Design and Implementation","score":0.9865999817848206,"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/T10860","display_name":"Speech and Audio Processing","score":0.9491000175476074,"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":0.7744941711425781},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.736310601234436},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7303892374038696},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7172945141792297},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5779397487640381},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.54916912317276},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4776674211025238},{"id":"https://openalex.org/keywords/duration","display_name":"Duration (music)","score":0.47172728180885315},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.45487815141677856},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42530497908592224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2756178379058838},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2569301128387451},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11140552163124084},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07391864061355591}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7744941711425781},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.736310601234436},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7303892374038696},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7172945141792297},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5779397487640381},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.54916912317276},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4776674211025238},{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.47172728180885315},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.45487815141677856},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42530497908592224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2756178379058838},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2569301128387451},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11140552163124084},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07391864061355591},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1985.1168222","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1985.1168222","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1826405859","https://openalex.org/W1945490744","https://openalex.org/W2098920026"],"related_works":["https://openalex.org/W2110375858","https://openalex.org/W2509918616","https://openalex.org/W1570840316","https://openalex.org/W2060409740","https://openalex.org/W4252671892","https://openalex.org/W2156505556","https://openalex.org/W2014919663","https://openalex.org/W2010376816","https://openalex.org/W1542588102","https://openalex.org/W1842536210"],"abstract_inverted_index":{"We":[0,143],"propose":[1],"a":[2,48,75,82,156,159],"new":[3],"method":[4],"of":[5,37,56,65,73,81,110,122,128,150,155,158,174],"synthesis":[6],"to":[7,30,91,107,125,138,170],"be":[8,168],"used":[9],"for":[10,147],"the":[11,44,52,54,62,92,100,103,108,117,129,140,151,172,175],"segment":[12,25,42,76,157,176],"vocoder,":[13,86],"which":[14,87],"transmits":[15],"intelligible":[16],"speech":[17,66,160],"at":[18,51],"rates":[19],"below":[20],"300":[21],"b/s.":[22],"The":[23,71],"earlier":[24],"vocoder":[26,77],"applies":[27],"LPC":[28,69,85],"analysis":[29],"input":[31,130],"speech,":[32],"divides":[33],"it":[34],"into":[35],"segments":[36,134],"variable":[38],"duration,":[39],"matches":[40],"each":[41,123],"with":[43,99],"nearest":[45,57,111],"template":[46,124],"from":[47],"codebook,":[49],"concatenates":[50],"receiver":[53],"set":[55,109],"templates,":[58,112],"and":[59,120,153,162],"finally":[60],"synthesizes":[61],"resultant":[63],"sequence":[64],"frames":[67],"using":[68],"synthesis.":[70],"quality":[72,173],"such":[74],"cannot":[78],"exceed":[79],"that":[80],"standard":[83],"unquantized":[84],"sounds":[88],"buzzy":[89],"due":[90],"pulse/noise":[93],"excitation":[94],"used.":[95],"Alternatively,":[96],"by":[97],"beginning":[98],"waveforms":[101],"(not":[102],"spectral":[104],"representation)":[105],"corresponding":[106],"we":[113],"can":[114,167],"independently":[115],"modify":[116],"pitch,":[118],"energy,":[119],"duration":[121,154],"match":[126],"those":[127],"segment.":[131],"These":[132],"modified":[133],"are":[135],"then":[136],"concatenated":[137],"produce":[139],"output":[141,178],"waveform.":[142],"present":[144],"here":[145],"methods":[146,166],"high-quality":[148],"modification":[149],"pitch":[152],"waveform":[161],"show":[163],"how":[164],"these":[165],"applied":[169],"improve":[171],"vocoder's":[177],"speech.":[179]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}