{"id":"https://openalex.org/W2294070564","doi":"https://doi.org/10.21437/interspeech.2013-19","title":"Pitch-gesture modeling using subband autocorrelation change detection","display_name":"Pitch-gesture modeling using subband autocorrelation change detection","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2294070564","doi":"https://doi.org/10.21437/interspeech.2013-19","mag":"2294070564"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-19","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5046802864","display_name":"Malcolm Slaney","orcid":"https://orcid.org/0000-0001-9733-4864"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malcolm Slaney","raw_affiliation_strings":["Institute of Electrical and Electronics Engineers"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Electronics Engineers","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107174154","display_name":"Elizabeth Shriberg","orcid":"https://orcid.org/0009-0004-3779-4956"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Elizabeth Shriberg","raw_affiliation_strings":["(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045413298","display_name":"Jui-Ting Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jui-Ting Huang","raw_affiliation_strings":["(Microsoft)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"(Microsoft)","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4696,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.60348584,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1911","last_page":"1915"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.717735767364502},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6949841976165771},{"id":"https://openalex.org/keywords/autocorrelation","display_name":"Autocorrelation","score":0.6465719938278198},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6297452449798584},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.611569344997406},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.593959629535675},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.4373367428779602},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4144544303417206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35631585121154785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13020384311676025}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717735767364502},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6949841976165771},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.6465719938278198},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6297452449798584},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.611569344997406},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.593959629535675},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.4373367428779602},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4144544303417206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35631585121154785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13020384311676025},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2013-19","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-19","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.681.2931","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.681.2931","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.slaney.org/malcolm/Microsoft/Slaney2013%28ToneWithoutPitch%29.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W23669922","https://openalex.org/W103244930","https://openalex.org/W126774805","https://openalex.org/W1495955104","https://openalex.org/W1544324307","https://openalex.org/W1592627291","https://openalex.org/W1863426813","https://openalex.org/W1966948181","https://openalex.org/W1971146038","https://openalex.org/W2059020775","https://openalex.org/W2063041593","https://openalex.org/W2091425152","https://openalex.org/W2103069945","https://openalex.org/W2135431242","https://openalex.org/W2142040441","https://openalex.org/W2142282591","https://openalex.org/W2151251521"],"related_works":["https://openalex.org/W1537109791","https://openalex.org/W2379831147","https://openalex.org/W2388176952","https://openalex.org/W2039878594","https://openalex.org/W2941168791","https://openalex.org/W2117854015","https://openalex.org/W2029025464","https://openalex.org/W2066867401","https://openalex.org/W2356656526","https://openalex.org/W2138039466"],"abstract_inverted_index":{"Calculating":[0],"speaker":[1],"pitch":[2,21,47,112],"(or":[3],"f0)":[4],"is":[5,22,123],"typically":[6],"the":[7,33,64,147,150],"first":[8],"computational":[9,53],"step":[10],"in":[11,45,51,63,128,140,152,170],"modeling":[12,46,92,168],"tone":[13,141],"and":[14,98,118,134,142,145],"intonation":[15,143],"for":[16,81,91,125,167],"spoken":[17],"language":[18],"understanding.":[19],"Usually":[20],"treated":[23],"as":[24,37,39],"a":[25,52,68,153],"fixed,":[26],"single-valued":[27],"quantity.":[28],"The":[29,106],"inherent":[30],"ambiguity":[31],"judging":[32],"octave":[34],"of":[35,108,120,130,149],"pitch,":[36],"well":[38],"spurious":[40],"values,":[41],"leads":[42],"to":[43,83,116],"errors":[44],"gestures":[48,169],"that":[49,59,160],"propagate":[50],"pipeline.":[54],"We":[55,137],"present":[56],"an":[57],"alternative":[58],"instead":[60],"measures":[61],"changes":[62],"harmonic":[65],"structure":[66],"using":[67],"subband":[69],"autocorrelation":[70,85],"change":[71],"detector":[72],"(SACD).":[73],"This":[74,122],"approach":[75,151],"builds":[76],"upon":[77],"new":[78],"machine-learning":[79],"ideas":[80],"how":[82],"integrate":[84,99],"information":[86,100],"across":[87],"subbands.":[88],"Importantly":[89],"however,":[90],"gestures,":[93],"we":[94],"preserve":[95],"multiple":[96],"hypotheses":[97],"from":[101],"all":[102],"harmonics":[103],"over":[104,110],"time.":[105],"benefits":[107],"SACD":[109,161],"standard":[111],"approaches":[113],"include":[114],"robustness":[115],"noise":[117],"amount":[119],"voicing.":[121],"important":[124],"real-world":[126],"data":[127],"terms":[129],"both":[131],"acoustic":[132],"conditions":[133],"speaking":[135],"style.":[136],"discuss":[138],"applications":[139],"modeling,":[144],"demonstrate":[146],"efficacy":[148],"Mandarin":[154],"Chinese":[155],"tone-classification":[156],"experiment.":[157],"Results":[158],"suggest":[159],"could":[162],"replace":[163],"conventional":[164],"pitch-based":[165],"methods":[166],"selected":[171],"spoken-language":[172],"processing":[173],"tasks.":[174]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"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"}
