{"id":"https://openalex.org/W2146562971","doi":"https://doi.org/10.1109/icassp.2005.1415138","title":"Speech Rate Estimation via Temporal Correlation and Selected Sub-Band Correlation","display_name":"Speech Rate Estimation via Temporal Correlation and Selected Sub-Band Correlation","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2146562971","doi":"https://doi.org/10.1109/icassp.2005.1415138","mag":"2146562971"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5010767866","display_name":"S. Narayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I144571360","display_name":"Viterbo University","ror":"https://ror.org/039p8pn96","country_code":"US","type":"education","lineage":["https://openalex.org/I144571360"]},{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"S. Narayanan","raw_affiliation_strings":["Speech Analysis and Interpretation Laboratory, USC Viterbi School of Engineering, USA","Speech Anal. & Interpretation Lab., Univ. of Southern California, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Analysis and Interpretation Laboratory, USC Viterbi School of Engineering, USA","institution_ids":["https://openalex.org/I144571360"]},{"raw_affiliation_string":"Speech Anal. & Interpretation Lab., Univ. of Southern California, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030096887","display_name":"May D. Wang","orcid":"https://orcid.org/0000-0003-3961-3608"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I144571360","display_name":"Viterbo University","ror":"https://ror.org/039p8pn96","country_code":"US","type":"education","lineage":["https://openalex.org/I144571360"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Wang","raw_affiliation_strings":["Speech Analysis and Interpretation Laboratory, USC Viterbi School of Engineering, USA","Speech Anal. & Interpretation Lab., Univ. of Southern California, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Analysis and Interpretation Laboratory, USC Viterbi School of Engineering, USA","institution_ids":["https://openalex.org/I144571360"]},{"raw_affiliation_string":"Speech Anal. & Interpretation Lab., Univ. of Southern California, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010767866"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I144571360"],"apc_list":null,"apc_paid":null,"fwci":2.5443,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.89588468,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"413","last_page":"416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9962999820709229,"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/estimator","display_name":"Estimator","score":0.7817752957344055},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.773383378982544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.598602294921875},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5765182375907898},{"id":"https://openalex.org/keywords/correlation-coefficient","display_name":"Correlation coefficient","score":0.5418338179588318},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.49256426095962524},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4731648564338684},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.45877206325531006},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.422486275434494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.327259361743927},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3094647526741028},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2589206397533417},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11816525459289551},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11432620882987976},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09855702519416809}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7817752957344055},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.773383378982544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.598602294921875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5765182375907898},{"id":"https://openalex.org/C2780092901","wikidata":"https://www.wikidata.org/wiki/Q3433612","display_name":"Correlation coefficient","level":2,"score":0.5418338179588318},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.49256426095962524},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4731648564338684},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.45877206325531006},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.422486275434494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.327259361743927},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3094647526741028},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2589206397533417},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11816525459289551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11432620882987976},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09855702519416809},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6499999761581421}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W36638734","https://openalex.org/W137732731","https://openalex.org/W173400130","https://openalex.org/W182299413","https://openalex.org/W200325626","https://openalex.org/W203970584","https://openalex.org/W1577618146","https://openalex.org/W1597349739","https://openalex.org/W1608645963","https://openalex.org/W1771302799","https://openalex.org/W2100336732","https://openalex.org/W2115501357","https://openalex.org/W2127894527","https://openalex.org/W2426479676","https://openalex.org/W3144168424","https://openalex.org/W4300639286","https://openalex.org/W6601463856","https://openalex.org/W6605534285","https://openalex.org/W6607058851","https://openalex.org/W6608116590","https://openalex.org/W6608257576","https://openalex.org/W6635795559","https://openalex.org/W6636294285","https://openalex.org/W6638027671","https://openalex.org/W6674893724"],"related_works":["https://openalex.org/W2372194214","https://openalex.org/W3081640970","https://openalex.org/W4200439127","https://openalex.org/W2021013714","https://openalex.org/W2120771489","https://openalex.org/W2412250669","https://openalex.org/W2051376034","https://openalex.org/W2359856669","https://openalex.org/W2078603735","https://openalex.org/W2955597484"],"abstract_inverted_index":{"In":[0],"this":[1,84],"paper,":[2],"we":[3,51],"propose":[4],"a":[5,87,96],"novel":[6,54],"method":[7,85],"for":[8,37],"speech":[9,15,100],"rate":[10,101],"estimation":[11,94],"without":[12],"requiring":[13],"automatic":[14],"recognition.":[16],"It":[17],"extends":[18],"the":[19,30,44,57,61,76,110,119,124],"methods":[20],"of":[21,32,43,63],"spectral":[22,35],"subband":[23],"correlation":[24,28,89,98],"by":[25],"including":[26],"temporal":[27],"and":[29,71,78,95,115],"use":[31,62],"selecting":[33,75],"prominent":[34],"subbands":[36],"correlation.":[38],"Furthermore,":[39],"to":[40],"address":[41],"some":[42,53],"practical":[45],"issues":[46],"in":[47],"previously":[48],"published":[49],"methods,":[50],"introduce":[52],"components":[55],"into":[56],"algorithm":[58],"such":[59],"as":[60],"pitch":[64],"confidence,":[65],"magnifying":[66],"window,":[67],"relative":[68,72],"peak":[69],"measure":[70],"threshold.":[73],"By":[74],"parameters":[77],"thresholds":[79],"from":[80],"realistic":[81],"development":[82],"sets,":[83],"achieves":[86],"0.972":[88],"coefficient":[90],"on":[91,99,123],"syllable":[92],"number":[93],"0.706":[97],"estimation.":[102],"This":[103],"result":[104],"is":[105],"about":[106],"6.9%":[107],"improvement":[108,117],"over":[109,118],"current":[111,120],"best":[112],"single":[113],"estimator":[114],"3.5%":[116],"multi-estimator,":[121],"evaluated":[122],"same":[125],"switchboard":[126],"database.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}