{"id":"https://openalex.org/W2576549984","doi":"https://doi.org/10.1109/apsipa.2016.7820792","title":"Performance estimation of spontaneous speech recognition using non-reference acoustic features","display_name":"Performance estimation of spontaneous speech recognition using non-reference acoustic features","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2576549984","doi":"https://doi.org/10.1109/apsipa.2016.7820792","mag":"2576549984"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2016.7820792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2016.7820792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","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/A5100512356","display_name":"Ling Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ling Guo","raw_affiliation_strings":["University of Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073170587","display_name":"Takeshi Yamada","orcid":"https://orcid.org/0000-0002-5744-8469"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takeshi Yamada","raw_affiliation_strings":["University of Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075702573","display_name":"Shoji Makino","orcid":"https://orcid.org/0000-0003-1934-640X"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoji Makino","raw_affiliation_strings":["University of Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100512356"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17446707,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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":0.8406169414520264},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7534530162811279},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5541978478431702},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.54786616563797},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5276899337768555},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5029420256614685},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.46650785207748413},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4424680471420288},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4273194670677185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4158342480659485},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3795863389968872},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.063211590051651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406169414520264},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7534530162811279},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5541978478431702},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.54786616563797},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5276899337768555},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5029420256614685},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.46650785207748413},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4424680471420288},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4273194670677185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4158342480659485},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3795863389968872},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.063211590051651},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2016.7820792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2016.7820792","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1501669607","https://openalex.org/W1988961123","https://openalex.org/W2004981122","https://openalex.org/W2034537249","https://openalex.org/W2085662862","https://openalex.org/W2151415191","https://openalex.org/W2153635508","https://openalex.org/W2158501878","https://openalex.org/W6630073874","https://openalex.org/W7073743773"],"related_works":["https://openalex.org/W2401827384","https://openalex.org/W2355290951","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W642007152","https://openalex.org/W2341426843","https://openalex.org/W2131711534"],"abstract_inverted_index":{"To":[0,107],"ensure":[1],"a":[2,13,50,113],"satisfactory":[3],"QoE":[4],"(Quality":[5],"of":[6,63,80,121,175],"Experience),":[7],"it":[8,31],"is":[9,32,131],"essential":[10],"to":[11,19,34,93,102,132],"establish":[12],"method":[14,115,146,178],"that":[15,137],"can":[16,45],"be":[17,46,91],"used":[18,48],"efficiently":[20],"investigate":[21],"recognition":[22,37,42,66,81,119,163],"performance":[23,38,62,82,120,164],"for":[24,59,116],"spontaneous":[25,94,122,182],"speech.":[26,143],"By":[27],"using":[28,166,181],"this":[29,109],"method,":[30],"allowed":[33],"monitor":[35],"the":[36,61,88,99,104,118,141,162,173,176,186],"in":[39,53],"providing":[40],"speech":[41,54,65,86,95,101,123,183],"services.":[43],"It":[44],"also":[47],"as":[49],"reliability":[51],"measure":[52],"dialogue":[55],"systems.":[56],"Previously,":[57],"methods":[58,89],"estimating":[60,117],"noisy":[64],"based":[67],"on":[68],"spectral":[69],"distortion":[70,105],"measures":[71],"have":[72],"been":[73],"proposed.":[74],"Although":[75],"they":[76,97],"give":[77],"an":[78],"estimate":[79],"without":[83],"actually":[84],"performing":[85],"recognition,":[87],"cannot":[90],"applied":[92],"because":[96],"require":[98,140],"reference":[100,142],"obtain":[103],"values.":[106],"solve":[108],"problem,":[110],"we":[111],"propose":[112],"novel":[114],"with":[124],"various":[125],"speaking":[126],"styles.":[127],"The":[128,144],"main":[129],"feature":[130],"use":[133],"non-reference":[134,148],"acoustic":[135],"features":[136,149],"do":[138],"not":[139],"proposed":[145,177],"extracts":[147],"by":[150,155,165,179],"openSMILE":[151],"(open-Source":[152],"Media":[153],"Interpretation":[154],"Large":[156],"feature-space":[157],"Extraction)":[158],"and":[159],"then":[160],"estimates":[161],"SVR":[167],"(Support":[168],"Vector":[169],"Regression).":[170],"We":[171],"confirmed":[172],"effectiveness":[174],"experiments":[180],"data":[184],"from":[185],"OGVC":[187],"(On-line":[188],"Gaming":[189],"Voice":[190],"Chat)":[191],"corpus.":[192]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}