{"id":"https://openalex.org/W2116687592","doi":"https://doi.org/10.1109/icassp.2011.5947538","title":"Very low bit-rate F0 coding for phonetic vocoder using MSD-HMM with quantized F0 context","display_name":"Very low bit-rate F0 coding for phonetic vocoder using MSD-HMM with quantized F0 context","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2116687592","doi":"https://doi.org/10.1109/icassp.2011.5947538","mag":"2116687592"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"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":"Takashi Nose","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","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":"Takao Kobayashi","raw_affiliation_strings":["Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"Interdisciplinary Graduate School of Science and Engineering Tokyo Institute of Technology Yokohama 226-8502 Japan","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":0.5396,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.63836753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"5236","last_page":"5239"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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/T10860","display_name":"Speech 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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9987000226974487,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8203542232513428},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7867341041564941},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7402852773666382},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6749353408813477},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5576128959655762},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.49238479137420654},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.488638699054718},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4498613476753235},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.42761123180389404},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41850242018699646},{"id":"https://openalex.org/keywords/bit-rate","display_name":"Bit rate","score":0.4131568670272827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38484102487564087},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32531726360321045},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.290659099817276},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16880139708518982}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8203542232513428},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7867341041564941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402852773666382},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6749353408813477},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5576128959655762},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.49238479137420654},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.488638699054718},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4498613476753235},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.42761123180389404},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41850242018699646},{"id":"https://openalex.org/C2987812609","wikidata":"https://www.wikidata.org/wiki/Q194158","display_name":"Bit rate","level":2,"score":0.4131568670272827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38484102487564087},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32531726360321045},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.290659099817276},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16880139708518982},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947538","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W22889032","https://openalex.org/W1935012542","https://openalex.org/W1963627370","https://openalex.org/W1996550570","https://openalex.org/W2000513720","https://openalex.org/W2049686551","https://openalex.org/W2100868147","https://openalex.org/W2136504711","https://openalex.org/W2154878481","https://openalex.org/W2166699153","https://openalex.org/W2166823384","https://openalex.org/W2167118415","https://openalex.org/W6680345554","https://openalex.org/W6684542345"],"related_works":["https://openalex.org/W2038801705","https://openalex.org/W2147186888","https://openalex.org/W2688184458","https://openalex.org/W2904846757","https://openalex.org/W1966606084","https://openalex.org/W2382520777","https://openalex.org/W2374333088","https://openalex.org/W2053531689","https://openalex.org/W2153067097","https://openalex.org/W1842536210"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,39,115],"very":[4],"low":[5],"bit-rate":[6,138],"F0":[7,22,30,35,47,95,105,130],"coding":[8],"technique":[9,127],"for":[10,59],"speaker-dependent":[11],"phonetic":[12],"vocoder":[13],"based":[14],"on":[15],"hidden":[16],"Markov":[17],"model":[18],"(HMM)":[19],"using":[20,42,79],"quantized":[21,46],"context.":[23],"In":[24],"the":[25,28,52,56,60,70,80,98,111,125,137],"proposed":[26,126],"technique,":[27],"input":[29,74],"sequence":[31,37],"is":[32,67,139],"converted":[33],"into":[34],"symbol":[36],"at":[38],"phoneme":[40],"level":[41],"scalar":[43],"quantization.":[44],"The":[45,64],"symbols":[48,96],"are":[49],"used":[50],"in":[51],"decoding":[53],"process":[54],"as":[55,97],"prosodic":[57],"context":[58],"HMM-based":[61,81],"speech":[62,66],"synthesis.":[63],"synthetic":[65],"generated":[68],"from":[69],"context-dependent":[71],"labels":[72],"and":[73,91,94],"speaker's":[75],"pre-trained":[76],"HMMs":[77],"by":[78],"parameter":[82],"generation":[83],"algorithm.":[84],"By":[85],"taking":[86],"account":[87,88],"of":[89,110,118],"preceding":[90],"succeeding":[92],"phonemes":[93],"contextual":[99],"factors,":[100],"we":[101],"can":[102,128],"generate":[103,129],"smooth":[104],"trajectory":[106],"similar":[107],"to":[108],"that":[109,124],"original":[112],"with":[113,132],"only":[114],"small":[116],"number":[117],"quantization":[119],"bits.":[120],"Experimental":[121],"results":[122],"demonstrate":[123],"contour":[131],"acceptable":[133],"quality":[134],"even":[135],"when":[136],"less":[140],"than":[141],"50":[142],"bps.":[143]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}