{"id":"https://openalex.org/W2076041950","doi":"https://doi.org/10.1109/icassp.2013.6639146","title":"Identification and modeling of word fragments in spontaneous speech","display_name":"Identification and modeling of word fragments in spontaneous speech","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2076041950","doi":"https://doi.org/10.1109/icassp.2013.6639146","mag":"2076041950"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Identification_and_modeling_of_word_fragments_in_spontaneous_speech/6473402","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062910836","display_name":"Yulia Tsvetkov","orcid":"https://orcid.org/0000-0002-4634-7128"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yulia Tsvetkov","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111476836","display_name":"Zaid Sheikh","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaid Sheikh","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.4576,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.61142706,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"7624","last_page":"7628"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983000159263611,"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":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.8631990551948547},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.763323187828064},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.761810302734375},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6276494860649109},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5848144888877869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5775027871131897},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5009090900421143},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.5005002021789551},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4754447937011719},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.45552098751068115},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.44477367401123047},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41772815585136414},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3162737786769867},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.30030614137649536},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1073102355003357}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8631990551948547},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.763323187828064},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.761810302734375},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6276494860649109},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5848144888877869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5775027871131897},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5009090900421143},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.5005002021789551},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4754447937011719},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.45552098751068115},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.44477367401123047},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41772815585136414},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3162737786769867},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.30030614137649536},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1073102355003357},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp.2013.6639146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:lti-1093","is_oa":false,"landing_page_url":"http://repository.cmu.edu/lti/96","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Technologies Institute","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6473402","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Journal contribution"},{"id":"pmh:oai:figshare.com:article/6473402","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Identification_and_modeling_of_word_fragments_in_spontaneous_speech/6473402","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.1184/r1/6473402.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473402.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473402","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Identification_and_modeling_of_word_fragments_in_spontaneous_speech/6473402","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W19416809","https://openalex.org/W147964346","https://openalex.org/W1846608861","https://openalex.org/W2085662862","https://openalex.org/W2095263712","https://openalex.org/W2100564077","https://openalex.org/W2124246394","https://openalex.org/W2133990480","https://openalex.org/W2134756243","https://openalex.org/W2153474519","https://openalex.org/W2153635508","https://openalex.org/W2155830326","https://openalex.org/W2166637769","https://openalex.org/W3202300147","https://openalex.org/W6600807020","https://openalex.org/W6802003531"],"related_works":["https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W2152945827","https://openalex.org/W2784059283","https://openalex.org/W2105439218","https://openalex.org/W2291624303"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,20,35,88,133],"novel":[4],"approach":[5,117],"to":[6,28,47,60,87,105],"handling":[7],"disfluencies,":[8],"word":[9],"fragments":[10],"and":[11,25,42,67],"self-interruption":[12],"points":[13],"in":[14,63,90],"Cantonese":[15],"conversational":[16,40,127],"speech.":[17],"We":[18,56,76],"train":[19],"classifier":[21,46],"that":[22,115],"exploits":[23],"lexical":[24],"acoustic":[26,53],"information":[27],"automatically":[29],"identify":[30],"disfluencies":[31,62,81],"during":[32],"training":[33],"of":[34,80,94,129],"speech":[36,130],"recognition":[37],"system":[38],"on":[39,70,120],"speech,":[41],"then":[43],"use":[44],"this":[45,116],"augment":[48],"reference":[49],"annotations":[50],"used":[51],"for":[52,124],"model":[54],"training.":[55],"experiment":[57],"with":[58,82],"approaches":[59],"modeling":[61],"the":[64,71,98,106,121,126],"pronunciation":[65],"dictionary,":[66],"their":[68],"effect":[69],"polyphonic":[72],"decision":[73],"tree":[74],"clustering.":[75],"achieve":[77],"automatic":[78],"detection":[79],"88%":[83],"accuracy,":[84],"which":[85,125],"leads":[86],"reduction":[89],"character":[91],"error":[92,101],"rate":[93],"1.9%":[95],"absolute.":[96],"While":[97],"high":[99],"baseline":[100],"rates":[102],"are":[103,109],"due":[104],"task":[107],"we":[108,113],"currently":[110],"working":[111],"on,":[112],"demonstrate":[114],"works":[118],"well":[119],"Switchboard":[122],"corpus,":[123],"nature":[128],"is":[131],"also":[132],"major":[134],"problem.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}