{"id":"https://openalex.org/W2153474519","doi":"https://doi.org/10.1109/icassp.2004.1326100","title":"The 2003 ISL rich transcription system for conversational telephony speech","display_name":"The 2003 ISL rich transcription system for conversational telephony speech","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2153474519","doi":"https://doi.org/10.1109/icassp.2004.1326100","mag":"2153474519"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5010878109","display_name":"Hagen Soltau","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"H. Soltau","raw_affiliation_strings":["Interactive Systems Laboratories, University of Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, University of Karlsruhe, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005656538","display_name":"Hua Yu","orcid":"https://orcid.org/0000-0002-0231-2978"},"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":"Hua Yu","raw_affiliation_strings":["Interactive Systems Laboratories, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"F. Metze","raw_affiliation_strings":["Interactive Systems Laboratories, University of Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, University of Karlsruhe, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048075735","display_name":"Christian F\u00fcgen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"C. Fugen","raw_affiliation_strings":["Interactive Systems Laboratories, University of Karlsruhe, Germany"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, University of Karlsruhe, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101665677","display_name":"Qin Jin","orcid":"https://orcid.org/0000-0003-4163-6067"},"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":"Qin Jin","raw_affiliation_strings":["Interactive Systems Laboratories, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014613234","display_name":"Szu-Chen Stan Jou","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":"Szu-Chen Jou","raw_affiliation_strings":["Interactive Systems Laboratories, Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Interactive Systems Laboratories, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5010878109"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.6213,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94835373,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"773"},"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":0.9986000061035156,"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":0.9954000115394592,"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":0.8191431760787964},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7414476871490479},{"id":"https://openalex.org/keywords/telephony","display_name":"Telephony","score":0.6635620594024658},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6500347852706909},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6288865208625793},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6125742793083191},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5720939636230469},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5129956603050232},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5082570910453796},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.49220243096351624},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.487505167722702},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.45507633686065674},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4356248378753662},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42641326785087585},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4029986262321472},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3701918125152588},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.1675911545753479},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08074429631233215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191431760787964},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7414476871490479},{"id":"https://openalex.org/C195358072","wikidata":"https://www.wikidata.org/wiki/Q944584","display_name":"Telephony","level":2,"score":0.6635620594024658},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6500347852706909},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6288865208625793},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6125742793083191},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5720939636230469},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5129956603050232},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5082570910453796},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.49220243096351624},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.487505167722702},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.45507633686065674},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4356248378753662},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42641326785087585},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4029986262321472},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3701918125152588},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.1675911545753479},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08074429631233215},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2004.1326100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.155.4457","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.155.4457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~scjou/paper/soltau_icassp04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1520957522","https://openalex.org/W1571931074","https://openalex.org/W1823291590","https://openalex.org/W2002342963","https://openalex.org/W2003123121","https://openalex.org/W2106554350","https://openalex.org/W2134756243","https://openalex.org/W6638410079","https://openalex.org/W6931557447"],"related_works":["https://openalex.org/W2149402184","https://openalex.org/W1566315437","https://openalex.org/W4221142855","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W2050138804","https://openalex.org/W767271433","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W2523799048"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"the":[3,110],"ISL":[4],"large":[5],"vocabulary":[6],"conversational":[7],"telephony":[8],"speech":[9],"recognition":[10],"system,":[11,82],"which":[12],"was":[13],"tested":[14],"in":[15],"NIST's":[16],"RT-03S":[17],"(\"Switchboard\")":[18],"evaluation.":[19],"We":[20,63],"present":[21,64],"our":[22,71,91],"experiments":[23],"on":[24,90,109],"improving":[25],"preprocessing,":[26],"acoustic":[27],"modelling,":[28],"and":[29,53],"language":[30,61],"modelling.":[31],"The":[32,96,106],"system":[33,98],"features":[34],"phone-dependent":[35],"semi-tied":[36,39],"full":[37],"covariances,":[38],"clustering":[40,43],"of":[41,51,60,70,88],"septa-phones,":[42],"across":[44],"phones,":[45],"feature":[46],"adaptive":[47],"training,":[48],"robust":[49],"estimation":[50],"VTLN":[52],"MLLR,":[54],"as":[55,57],"well":[56],"context-dependent":[58],"interpolation":[59],"models.":[62],"detailed":[65],"results":[66],"for":[67],"each":[68],"stage":[69],"multi-pass":[72],"transcription":[73],"scheme.":[74],"System":[75],"development":[76,94],"started":[77],"with":[78],"a":[79,84,102],"1997":[80],"SWB":[81],"yielding":[83],"word":[85],"error":[86,107],"rate":[87,108],"35.1%":[89],"internal":[92],"1h":[93],"set.":[95],"final":[97],"performed":[99],"at":[100],"21.8%,":[101],"38%":[103],"relative":[104],"improvement.":[105],"RT-03":[111],"CTS":[112],"evaluation":[113],"set":[114],"is":[115],"23.4%.":[116]},"counts_by_year":[{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}