{"id":"https://openalex.org/W2169998051","doi":"https://doi.org/10.1109/icassp.2003.1198753","title":"Prosodic knowledge sources for automatic speech recognition","display_name":"Prosodic knowledge sources for automatic speech recognition","publication_year":2003,"publication_date":"2003-11-20","ids":{"openalex":"https://openalex.org/W2169998051","doi":"https://doi.org/10.1109/icassp.2003.1198753","mag":"2169998051"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198753","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5060715364","display_name":"Dimitra Vergyri","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Vergyri","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060979948","display_name":"Andreas Stolcke","orcid":"https://orcid.org/0000-0002-9925-905X"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Stolcke","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108383529","display_name":"V.R.R. Gadde","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"V.R.R. Gadde","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056267912","display_name":"Luciana Ferrer","orcid":"https://orcid.org/0000-0002-0426-8683"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Ferrer","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108097106","display_name":"E. Shriberg","orcid":null},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"E. Shriberg","raw_affiliation_strings":["Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Technology and Research Laboratory, SRI International, Inc., Menlo Park, CA, USA","institution_ids":["https://openalex.org/I1298353152"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1298353152"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9977999925613403,"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/T12031","display_name":"Speech and dialogue systems","score":0.9977999925613403,"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/prosody","display_name":"Prosody","score":0.7967687845230103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7653283476829529},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7552331686019897},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7169981598854065},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5193561315536499},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5185911655426025},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4869597852230072},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.48290205001831055},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46284955739974976},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4579533338546753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43175357580184937},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.41861313581466675},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.28339332342147827},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18067458271980286}],"concepts":[{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.7967687845230103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7653283476829529},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7552331686019897},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7169981598854065},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5193561315536499},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5185911655426025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4869597852230072},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.48290205001831055},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46284955739974976},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4579533338546753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43175357580184937},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.41861313581466675},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.28339332342147827},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18067458271980286},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2003.1198753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198753","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.6701","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.6701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-speech.sri.com/cgi-bin/run-distill?papers/icassp2003-prosodyasr.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.9.938","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.9.938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-speech.sri.com/papers/icassp2003-prosodyasr.ps.gz","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7599999904632568,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W61566120","https://openalex.org/W1577006985","https://openalex.org/W1582730572","https://openalex.org/W1877154798","https://openalex.org/W1959963859","https://openalex.org/W1990387894","https://openalex.org/W2032751491","https://openalex.org/W2062093483","https://openalex.org/W2112882007","https://openalex.org/W2146451076","https://openalex.org/W2426479676","https://openalex.org/W6602520203","https://openalex.org/W6634727054","https://openalex.org/W6676921367"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W4214652783","https://openalex.org/W258725851","https://openalex.org/W2060642356","https://openalex.org/W2042011703","https://openalex.org/W1661933970","https://openalex.org/W2161314515","https://openalex.org/W2403645569"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"different":[3,21,68,121],"prosodic":[4,71,85,101,122],"knowledge":[5,102],"sources":[6],"are":[7],"integrated":[8],"into":[9],"a":[10,31,43,67],"state-of-the-art":[11],"large":[12],"vocabulary":[13],"speech":[14,25,126],"recognition":[15],"system.":[16],"Prosody":[17],"manifests":[18],"itself":[19],"on":[20,91],"levels":[22],"in":[23,33,38,45,73],"the":[24,28,40,46,51,88,92,110,125],"signal:":[26],"within":[27],"words":[29,41,82],"as":[30,42],"change":[32],"phone":[34],"durations":[35],"and":[36,49,58],"pitch,":[37],"between":[39],"variation":[44],"pause":[47],"length,":[48],"beyond":[50],"words,":[52],"correlating":[53],"with":[54,99,109],"higher":[55],"linguistic":[56],"structures":[57],"nonlexical":[59],"phenomena.":[60],"We":[61],"investigate":[62],"three":[63],"models,":[64,114],"each":[65,100,118],"exploiting":[66],"level":[69],"of":[70,87,112,124],"information,":[72],"rescoring":[74],"N-best":[75],"hypotheses":[76],"according":[77],"to":[78,84],"how":[79],"well":[80],"recognized":[81],"correspond":[83],"features":[86],"utterance.":[89],"Experiments":[90],"Switchboard":[93],"corpus":[94],"show":[95],"word":[96],"accuracy":[97],"improvements":[98],"source.":[103],"A":[104],"further":[105],"improvement":[106],"is":[107],"observed":[108],"combination":[111],"all":[113],"demonstrating":[115],"that":[116],"they":[117],"capture":[119],"somewhat":[120],"characteristics":[123],"signal.":[127]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}