{"id":"https://openalex.org/W2399934308","doi":"https://doi.org/10.1109/icassp.2016.7472678","title":"Online speaking rate estimation using recurrent neural networks","display_name":"Online speaking rate estimation using recurrent neural networks","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2399934308","doi":"https://doi.org/10.1109/icassp.2016.7472678","mag":"2399934308"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5109394386","display_name":"Yishan Jiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yishan Jiao","raw_affiliation_strings":["Department of Speech and Hearing Science"],"affiliations":[{"raw_affiliation_string":"Department of Speech and Hearing Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102334100","display_name":"Ming Tu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ming Tu","raw_affiliation_strings":["Department of Speech and Hearing Science"],"affiliations":[{"raw_affiliation_string":"Department of Speech and Hearing Science","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021646973","display_name":"Visar Berisha","orcid":"https://orcid.org/0000-0001-8804-8874"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Visar Berisha","raw_affiliation_strings":["Department of Speech and Hearing Science","School of Electrical, Computer, Energy Engineering, Arizona State University"],"affiliations":[{"raw_affiliation_string":"Department of Speech and Hearing Science","institution_ids":[]},{"raw_affiliation_string":"School of Electrical, Computer, Energy Engineering, Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056934840","display_name":"Julie Liss","orcid":"https://orcid.org/0000-0001-8782-2901"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Julie Liss","raw_affiliation_strings":["Department of Speech and Hearing Science"],"affiliations":[{"raw_affiliation_string":"Department of Speech and Hearing Science","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5109394386"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9991,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.9439151,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5245","last_page":"5249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8032780885696411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7859224677085876},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.723904550075531},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5817303657531738},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5603175163269043},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.5229752063751221},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.477062851190567},{"id":"https://openalex.org/keywords/long-short-term-memory","display_name":"Long short term memory","score":0.47301486134529114},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4699794352054596},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4484010338783264},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.42161834239959717},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4212018847465515},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.41367119550704956},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40018221735954285}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8032780885696411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7859224677085876},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.723904550075531},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5817303657531738},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5603175163269043},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.5229752063751221},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.477062851190567},{"id":"https://openalex.org/C133488467","wikidata":"https://www.wikidata.org/wiki/Q6673524","display_name":"Long short term memory","level":4,"score":0.47301486134529114},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4699794352054596},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4484010338783264},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.42161834239959717},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4212018847465515},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.41367119550704956},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40018221735954285},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/icassp.2016.7472678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W173400130","https://openalex.org/W304834817","https://openalex.org/W1598253959","https://openalex.org/W1965635292","https://openalex.org/W1998628338","https://openalex.org/W2018882848","https://openalex.org/W2024663388","https://openalex.org/W2034215893","https://openalex.org/W2042071805","https://openalex.org/W2048497537","https://openalex.org/W2049515993","https://openalex.org/W2064675550","https://openalex.org/W2081318766","https://openalex.org/W2098396290","https://openalex.org/W2117903328","https://openalex.org/W2122585011","https://openalex.org/W2129244720","https://openalex.org/W2143612262","https://openalex.org/W2156142001","https://openalex.org/W2166637769","https://openalex.org/W2171907819","https://openalex.org/W2171928131","https://openalex.org/W6610843619","https://openalex.org/W6635996524"],"related_works":["https://openalex.org/W2912153778","https://openalex.org/W4288108708","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W4387163678","https://openalex.org/W2973430807","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W4385280324","https://openalex.org/W2098529290"],"abstract_inverted_index":{"A":[0],"reliable":[1],"online":[2,25],"speaking":[3,26,81,153],"rate":[4,27,37,82,124,128],"estimation":[5,28,83],"tool":[6],"is":[7,38],"useful":[8],"in":[9,152],"many":[10,48],"domains,":[11],"including":[12],"speech":[13,15,98,106,112,140],"recognition,":[14],"therapy":[16],"intervention,":[17],"speaker":[18],"identification,":[19],"etc.":[20],"This":[21],"paper":[22],"proposes":[23],"an":[24,53],"model":[29],"based":[30],"on":[31,46,94,110,137],"recurrent":[32],"neural":[33],"networks":[34],"(RNNs).":[35],"Speaking":[36],"a":[39,76,88,95,118],"long-term":[40,65,148],"feature":[41],"of":[42,70,97],"speech,":[43],"which":[44],"depends":[45],"how":[47],"syllables":[49],"were":[50],"spoken":[51],"over":[52],"extended":[54],"time":[55],"window":[56],"(seconds).":[57],"We":[58],"posit":[59],"that":[60,100,114,142],"since":[61],"RNNs":[62],"can":[63,146],"capture":[64,147],"dependencies":[66],"through":[67],"the":[68,80,115,122,126,132,143],"memory":[69,91],"previous":[71],"hidden":[72],"states,":[73],"they":[74],"are":[75,101],"good":[77],"match":[78],"for":[79],"task.":[84],"Here":[85],"we":[86],"train":[87],"long":[89],"short-term":[90,150],"(LSTM)":[92],"RNN":[93],"set":[96],"features":[99],"known":[102],"to":[103,131],"correlate":[104],"with":[105],"rhythm.":[107],"An":[108],"evaluation":[109,136],"spontaneous":[111],"shows":[113,141],"method":[116,145],"yields":[117],"higher":[119],"correlation":[120],"between":[121],"estimated":[123],"and":[125,149],"ground-truth":[127],"when":[129],"compared":[130],"state-of-the-art":[133],"alternatives.":[134],"The":[135],"longitudinal":[138],"pathological":[139],"proposed":[144],"changes":[151],"rate.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}