{"id":"https://openalex.org/W2141592580","doi":"https://doi.org/10.1109/icassp.2008.4518789","title":"Modeling the intonation of discourse segments for improved online dialog ACT tagging","display_name":"Modeling the intonation of discourse segments for improved online dialog ACT tagging","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2141592580","doi":"https://doi.org/10.1109/icassp.2008.4518789","mag":"2141592580","pmid":"https://pubmed.ncbi.nlm.nih.gov/19132136"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518789","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2614672","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112911746","display_name":"Vivek Kumar Rangarajan Sridhar","orcid":null},"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":true,"raw_author_name":"Vivek Kumar Rangarajan Sridhar","raw_affiliation_strings":["Speech Analysis and Interpretation Laboratory, Viterbi School of Engineering, University of Southern California, USA"],"affiliations":[{"raw_affiliation_string":"Speech Analysis and Interpretation Laboratory, Viterbi School of Engineering, University of Southern California, USA","institution_ids":["https://openalex.org/I144571360","https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"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":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Speech Analysis and Interpretation Laboratory, Viterbi School of Engineering, University of Southern California, USA","Speech Anal. & Interpretation Lab., Univ. of Southern California, Los Angeles, CA"],"affiliations":[{"raw_affiliation_string":"Speech Analysis and Interpretation Laboratory, Viterbi School of Engineering, University of Southern California, USA","institution_ids":["https://openalex.org/I144571360","https://openalex.org/I1174212"]},{"raw_affiliation_string":"Speech Anal. & Interpretation Lab., Univ. of Southern California, Los Angeles, CA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111475783","display_name":"Srinivas Bangalore","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivas Bangalore","raw_affiliation_strings":["AT and T Research Laboratories, Florham Park, NJ, USA","AT&T Labs\u2014Research, 180 Park Avenue, Florham Park, NJ 07932, U.S.A"],"affiliations":[{"raw_affiliation_string":"AT and T Research Laboratories, Florham Park, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Labs\u2014Research, 180 Park Avenue, Florham Park, NJ 07932, U.S.A","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112911746"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I144571360"],"apc_list":null,"apc_paid":null,"fwci":1.0722,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.74568421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"4518789","issue":null,"first_page":"5033","last_page":"5036"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T12031","display_name":"Speech and dialogue systems","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/T10181","display_name":"Natural Language Processing Techniques","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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9970999956130981,"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/dialog-box","display_name":"Dialog box","score":0.7975047826766968},{"id":"https://openalex.org/keywords/intonation","display_name":"Intonation (linguistics)","score":0.7554184198379517},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7526339888572693},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5727320909500122},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.4633375406265259},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.43838974833488464},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4292775094509125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3279959559440613},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2732595205307007}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7975047826766968},{"id":"https://openalex.org/C2781045179","wikidata":"https://www.wikidata.org/wiki/Q5576720","display_name":"Intonation (linguistics)","level":2,"score":0.7554184198379517},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526339888572693},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5727320909500122},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.4633375406265259},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.43838974833488464},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4292775094509125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3279959559440613},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2732595205307007},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2008.4518789","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518789","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmid:19132136","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/19132136","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:2614672","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2614672","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:2614672","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2614672","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc IEEE Int Conf Acoust Speech Signal Process","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7300000190734863,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W9486812","https://openalex.org/W158901718","https://openalex.org/W1570448133","https://openalex.org/W1576632330","https://openalex.org/W2019099223","https://openalex.org/W2112078429","https://openalex.org/W2112126372","https://openalex.org/W2128970689","https://openalex.org/W2949089885","https://openalex.org/W6676737319"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2394821827","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2920931047","https://openalex.org/W1977846844"],"abstract_inverted_index":{"Prosody":[0],"is":[1],"an":[2],"important":[3],"cue":[4],"for":[5,29],"identifying":[6],"dialog":[7,30],"acts.":[8],"In":[9],"this":[10],"paper,":[11],"we":[12,108],"show":[13],"that":[14,40,59,93],"modeling":[15],"the":[16,45,64,86,118],"sequence":[17],"of":[18,44,51,66,114,125],"acoustic-prosodic":[19],"values":[20],"as":[21],"n-gram":[22],"features":[23],"with":[24,122],"a":[25,56,76,110],"maximum":[26],"entropy":[27],"model":[28],"act":[31],"(DA)":[32],"tagging":[33,81,112],"can":[34,94],"perform":[35],"better":[36],"than":[37],"conventional":[38],"approaches":[39],"use":[41],"coarse":[42],"representation":[43],"prosodic":[46,69,102],"contour":[47],"through":[48],"acoustic":[49],"correlates":[50],"prosody.":[52],"We":[53],"also":[54],"propose":[55],"discriminative":[57],"framework":[58],"exploits":[60],"preceding":[61],"context":[62],"in":[63,85,131],"form":[65],"lexical":[67,100],"and":[68,82,101],"cues":[70,103],"from":[71,104],"previous":[72,106,126],"discourse":[73],"segments.":[74],"Such":[75],"scheme":[77],"facilitates":[78],"online":[79],"DA":[80,111,127],"offers":[83],"robustness":[84],"decoding":[87,91],"process,":[88],"unlike":[89],"greedy":[90],"schemes":[92],"potentially":[95],"propagate":[96],"errors.":[97],"Using":[98],"only":[99],"3":[105],"utterances,":[107],"achieve":[109],"accuracy":[113],"72%":[115],"compared":[116],"to":[117],"best":[119],"case":[120],"scenario":[121],"accurate":[123],"knowledge":[124],"tag,":[128],"which":[129],"results":[130],"74%":[132],"accuracy.":[133]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2016-06-24T00:00:00"}