{"id":"https://openalex.org/W2162983044","doi":"https://doi.org/10.1109/icassp.2002.5743746","title":"A phase generation method for speech reconstruction from spectral envelope and pitch intervals","display_name":"A phase generation method for speech reconstruction from spectral envelope and pitch intervals","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2162983044","doi":"https://doi.org/10.1109/icassp.2002.5743746","mag":"2162983044"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743746","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/A5056128107","display_name":"Hong-Goo Kang","orcid":"https://orcid.org/0000-0002-6554-0783"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hong-Goo Kang","raw_affiliation_strings":["AT and T Research Laboratories, Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085604883","display_name":"Hong Kook Kim","orcid":"https://orcid.org/0000-0002-0105-6693"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hong Kook Kim","raw_affiliation_strings":["AT and T Research Laboratories, Florham Park, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056128107"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":0.3241,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.50125104,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"I","last_page":"429"},"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/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.7022924423217773},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.7020732164382935},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6692559123039246},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6662141680717468},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.6562181711196899},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5356563925743103},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5205898284912109},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.5108091831207275},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49138155579566956},{"id":"https://openalex.org/keywords/codec2","display_name":"Codec2","score":0.4813988208770752},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4556678831577301},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.43374699354171753},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.4332851469516754},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.4193994700908661},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27322298288345337},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12392136454582214}],"concepts":[{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.7022924423217773},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.7020732164382935},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6692559123039246},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662141680717468},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6562181711196899},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5356563925743103},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5205898284912109},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.5108091831207275},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49138155579566956},{"id":"https://openalex.org/C75217168","wikidata":"https://www.wikidata.org/wiki/Q1105653","display_name":"Codec2","level":4,"score":0.4813988208770752},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4556678831577301},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.43374699354171753},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.4332851469516754},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.4193994700908661},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27322298288345337},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12392136454582214},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743746","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743746","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W183623625","https://openalex.org/W1591492847","https://openalex.org/W1951264251","https://openalex.org/W2107494014","https://openalex.org/W2131094339","https://openalex.org/W2136645678","https://openalex.org/W2148154194","https://openalex.org/W2164764235"],"related_works":["https://openalex.org/W2383072803","https://openalex.org/W2378944441","https://openalex.org/W2068677590","https://openalex.org/W2536737918","https://openalex.org/W2031734417","https://openalex.org/W254215651","https://openalex.org/W2223500991","https://openalex.org/W1570840316","https://openalex.org/W3140802561","https://openalex.org/W2164373835"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,75],"propose":[4],"a":[5,24,30,41,49,54,58,65,121,136,155],"new":[6],"speech":[7,26,37,74,108,163],"reconstruction":[8],"method":[9,147,176],"from":[10,120,139],"spectral":[11,34],"envelope":[12,35],"and":[13,84,100],"pitch":[14,152],"intervals,":[15],"which":[16],"is":[17,38,48,61,91,114,134,154,177],"applicable":[18],"to":[19,63,125],"the":[20,70,73,77,95,104,111,117,126,131,140,149,159,171,174,183],"network":[21],"side":[22],"of":[23,36,43,72,158,173,182],"distributed":[25],"recognition":[27,51],"system":[28],"as":[29,40],"play-back":[31],"function.":[32],"The":[33,87,143],"represented":[39],"set":[42],"mel-frequency":[44],"cepstral":[45],"coefficients":[46],"that":[47,151,170,181],"well-known":[50],"parameter.":[52],"First,":[53],"sinusoidal":[55],"synthesis":[56],"with":[57,81],"zero-phase":[59],"model":[60],"used":[62],"obtain":[64],"pitch-based":[66,127],"waveform.":[67],"To":[68],"enhance":[69],"naturalness":[71],"replace":[76],"zero":[78],"phase":[79,89,132,145],"information":[80,90,133],"pre-stored":[82],"linear":[83,99],"random":[85,101],"codebooks.":[86],"ultimate":[88],"determined":[92],"depending":[93],"on":[94],"energy":[96,112],"ratio":[97,113],"between":[98],"components.":[102],"Unlike":[103],"classic":[105],"low":[106],"bit-rate":[107],"coding,":[109],"however,":[110],"estimated":[115],"in":[116,162],"decoding":[118],"stage":[119],"time-frequency":[122],"filter":[123],"applied":[124],"synthesized":[128],"signal.":[129],"Thus,":[130],"not":[135],"feature":[137],"parameter":[138],"encoder":[141],"side.":[142],"proposed":[144,175],"generation":[146],"uses":[148],"knowledge":[150],"variation":[153],"main":[156],"cause":[157],"mixed":[160],"characteristics":[161],"signals.":[164],"An":[165],"informal":[166],"listening":[167],"test":[168],"verifies":[169],"quality":[172],"much":[178],"better":[179],"than":[180],"synthetic":[184],"quality.":[185]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}