{"id":"https://openalex.org/W2100868147","doi":"https://doi.org/10.1109/icassp.1998.675338","title":"A very low bit rate speech coder using HMM-based speech recognition/synthesis techniques","display_name":"A very low bit rate speech coder using HMM-based speech recognition/synthesis techniques","publication_year":2002,"publication_date":"2002-11-27","ids":{"openalex":"https://openalex.org/W2100868147","doi":"https://doi.org/10.1109/icassp.1998.675338","mag":"2100868147"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1998.675338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5103023678","display_name":"Keiichi Tokuda","orcid":"https://orcid.org/0000-0001-6143-0133"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"K. Tokuda","raw_affiliation_strings":["Dept. of Computer Science, Nagoya Institute of Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science, Nagoya Institute of Technology, Japan","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064866374","display_name":"Takashi Masuko","orcid":"https://orcid.org/0000-0002-2410-2007"},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Masuko","raw_affiliation_strings":["Nagoya Inst. of Technol.#TAB#"],"affiliations":[{"raw_affiliation_string":"Nagoya Inst. of Technol.#TAB#","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060655839","display_name":"Jun Hiroi","orcid":null},"institutions":[{"id":"https://openalex.org/I197274945","display_name":"Nagoya Institute of Technology","ror":"https://ror.org/055yf1005","country_code":"JP","type":"education","lineage":["https://openalex.org/I197274945"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"J. Hiroi","raw_affiliation_strings":["Nagoya Inst. of Technol.#TAB#"],"affiliations":[{"raw_affiliation_string":"Nagoya Inst. of Technol.#TAB#","institution_ids":["https://openalex.org/I197274945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022405100","display_name":"Takao Kobayashi","orcid":"https://orcid.org/0000-0003-0387-8030"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Kobayashi","raw_affiliation_strings":["Tokyo Inst. of Tech."],"affiliations":[{"raw_affiliation_string":"Tokyo Inst. of Tech.","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059137996","display_name":"Tadashi Kitamura","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Kitamura","raw_affiliation_strings":["Tokyo Inst. of Tech."],"affiliations":[{"raw_affiliation_string":"Tokyo Inst. of Tech.","institution_ids":["https://openalex.org/I114531698"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.565,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":38,"citation_normalized_percentile":{"value":0.892327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":91},"biblio":{"volume":"2","issue":null,"first_page":"609","last_page":"612"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9998,"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":0.9998,"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/T10860","display_name":"Speech and Audio Processing","score":0.9969,"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":0.9954,"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/cepstrum","display_name":"Cepstrum","score":0.5576627}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.84030634},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8130403},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7015445},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.6098085},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5576627},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.51701033},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.42531174},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39375058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35893983}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1998.675338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.52,"display_name":"Peace, justice, and strong institutions","id":"https://metadata.un.org/sdg/16"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":12,"referenced_works":["https://openalex.org/W115545536","https://openalex.org/W1826405859","https://openalex.org/W1935012542","https://openalex.org/W193742919","https://openalex.org/W1988378063","https://openalex.org/W2093450784","https://openalex.org/W2096555739","https://openalex.org/W2124453323","https://openalex.org/W2144139079","https://openalex.org/W22889032","https://openalex.org/W3036802551","https://openalex.org/W86457398"],"related_works":["https://openalex.org/W2534663775","https://openalex.org/W2363301696","https://openalex.org/W2167131998","https://openalex.org/W2167107465","https://openalex.org/W2161287643","https://openalex.org/W2160220319","https://openalex.org/W2140099343","https://openalex.org/W2115984063","https://openalex.org/W2106898123","https://openalex.org/W1570840316"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,47,120],"very":[4],"low":[5],"bit":[6],"rate":[7],"speech":[8,63,71],"coder":[9,104],"based":[10],"on":[11],"HMM":[12,58],"(hidden":[13],"Markov":[14],"model).":[15],"The":[16],"encoder":[17],"carries":[18],"out":[19],"phoneme":[20,24,37,44],"recognition,":[21],"and":[22,28,46],"transmits":[23],"indexes,":[25,45],"state":[26],"durations":[27],"pitch":[29,91,131],"information":[30],"to":[31,42,89,119],"the":[32,35,43,56,74,90,99,102,110],"decoder.":[33],"In":[34],"decoder,":[36],"HMMs":[38],"are":[39,83],"concatenated":[40,57],"according":[41,88],"sequence":[48],"of":[49,101],"mel-cepstral":[50,86],"coefficient":[51],"vectors":[52],"is":[53,117],"generated":[54],"from":[55],"by":[59,72,85],"using":[60],"an":[61],"ML-based":[62],"parameter":[64],"generation":[65],"technique.":[66],"Finally":[67],"we":[68],"obtain":[69],"synthetic":[70],"exciting":[73],"MLSA":[75],"(mel":[76],"log":[77],"spectrum":[78],"approximation)":[79],"filter,":[80],"whose":[81],"coefficients":[82],"given":[84],"coefficients,":[87],"information.":[92],"A":[93],"subjective":[94],"listening":[95],"test":[96,111],"shows":[97],"that":[98],"performance":[100],"proposed":[103],"at":[105,123],"about":[106],"150":[107],"bit/s":[108,125],"(for":[109],"data":[112],"including":[113],"26%":[114],"silence":[115],"region)":[116],"comparable":[118],"VQ-based":[121],"vocoder":[122],"400":[124],"(=8":[126],"bit/frame/spl":[127],"times/50":[128],"frame/s)":[129],"without":[130],"quantization":[132],"for":[133],"both":[134],"coders.":[135]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2100868147","counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2024-12-24T14:21:28.790955","created_date":"2016-06-24"}