{"id":"https://openalex.org/W2140537255","doi":"https://doi.org/10.1109/icassp.2004.1326095","title":"Generating and evaluating segmentations for automatic speech recognition of conversational telephone speech","display_name":"Generating and evaluating segmentations for automatic speech recognition of conversational telephone speech","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2140537255","doi":"https://doi.org/10.1109/icassp.2004.1326095","mag":"2140537255"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326095","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/A5031993584","display_name":"S.E. Tranter","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"S.E. Tranter","raw_affiliation_strings":["Cambridge University Engineering Department, Cambridge, UK","Dept. of Eng., Cambridge Univ., UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Dept. of Eng., Cambridge Univ., UK#TAB#","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"K. Yu","raw_affiliation_strings":["Cambridge University Engineering Department, Cambridge, UK","University of Cambridge, Cambridge, Cambridgeshire, GB","Dept. of Eng., Cambridge Univ., UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"University of Cambridge, Cambridge, Cambridgeshire, GB","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Dept. of Eng., Cambridge Univ., UK#TAB#","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068011771","display_name":"G. Everinann","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"G. Everinann","raw_affiliation_strings":["Dept. of Eng., Cambridge Univ., UK","Dept. of Eng., Cambridge Univ., UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Dept. of Eng., Cambridge Univ., UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Dept. of Eng., Cambridge Univ., UK#TAB#","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P.C. Woodland","raw_affiliation_strings":["Cambridge University Engineering Department, Cambridge, UK","Dept. of Eng., Cambridge Univ., UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Cambridge University Engineering Department, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Dept. of Eng., Cambridge Univ., UK#TAB#","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031993584"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":1.4021,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.82450653,"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":"I","last_page":"753"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9977999925613403,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-recognition","display_name":"Speech recognition","score":0.7922532558441162},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7902709245681763},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4817054867744446},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4485005736351013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37697941064834595}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7922532558441162},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7902709245681763},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4817054867744446},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4485005736351013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37697941064834595}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326095","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326095","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W136679770","https://openalex.org/W2115407392","https://openalex.org/W2163295968","https://openalex.org/W2179562937","https://openalex.org/W2188293537","https://openalex.org/W4285719527","https://openalex.org/W6605623754","https://openalex.org/W6685848937","https://openalex.org/W6687026376"],"related_works":["https://openalex.org/W2611614995","https://openalex.org/W2368651715","https://openalex.org/W2789919619","https://openalex.org/W1552159754","https://openalex.org/W2148757832","https://openalex.org/W4321496520","https://openalex.org/W2293457016","https://openalex.org/W3107474891","https://openalex.org/W2368779261","https://openalex.org/W2374918184"],"abstract_inverted_index":{"Speech":[0],"recognition":[1,29],"systems":[2],"for":[3,127],"conversational":[4],"telephone":[5],"speech":[6,18,62],"require":[7],"the":[8,28,40,58,61,85,97,125],"audio":[9,25],"data":[10,115],"to":[11,36,109],"be":[12,110,121],"automatically":[13],"divided":[14],"into":[15],"regions":[16],"of":[17,23,84],"and":[19,38,56,88,105],"non-speech.":[20],"The":[21],"quality":[22],"this":[24,89],"segmentation":[26,37,79,103],"affects":[27],"accuracy.":[30],"This":[31],"paper":[32],"describes":[33],"several":[34],"approaches":[35],"compares":[39],"resulting":[41],"recogniser":[42,63],"performance.":[43],"It":[44],"is":[45,107],"shown":[46,108],"that":[47,118],"using":[48,57,91],"Gaussian":[49],"mixture":[50],"models":[51],"outperforms":[52],"an":[53,100],"energy-detection":[54],"method":[55],"output":[59],"from":[60,80],"itself":[64],"increases":[65],"performance":[66,73],"further.":[67],"An":[68],"upper":[69],"bound":[70],"on":[71],"possible":[72],"was":[74],"obtained":[75],"when":[76],"deriving":[77],"a":[78,81],"forced":[82],"alignment":[83],"reference":[86],"words":[87],"outperformed":[90],"manually":[92],"marked":[93],"word":[94],"times.":[95],"Finally":[96],"correlation":[98],"between":[99],"appropriately":[101],"defined":[102],"score":[104],"WER":[106],"over":[111],"0.95":[112],"across":[113],"three":[114],"sets,":[116],"suggesting":[117],"segmentations":[119],"can":[120],"evaluated":[122],"directly":[123],"without":[124],"need":[126],"full":[128],"decoding":[129],"runs.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}