{"id":"https://openalex.org/W2106033504","doi":"https://doi.org/10.1109/asru.2007.4430157","title":"A Mandarin lecture speech transcription system for speech summarization","display_name":"A Mandarin lecture speech transcription system for speech summarization","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2106033504","doi":"https://doi.org/10.1109/asru.2007.4430157","mag":"2106033504"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2007.4430157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition &amp; Understanding (ASRU)","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/A5110325576","display_name":"Ho Yin Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ho Yin Chan","raw_affiliation_strings":["Human Language Technology Center, Electronic and Computer Engineering, University of Science and Technology (HKUST), Kowloon, Hong Kong, China","University of Science and Technology (Hong Kong)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center, Electronic and Computer Engineering, University of Science and Technology (HKUST), Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"University of Science and Technology (Hong Kong)","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052968355","display_name":"Justin Jian Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Justin Jian Zhang","raw_affiliation_strings":["Human Language Technology Center, Electronic and Computer Engineering, University of Science and Technology (HKUST), Kowloon, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center, Electronic and Computer Engineering, University of Science and Technology (HKUST), Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065856469","display_name":"Pascale Fung","orcid":"https://orcid.org/0000-0002-0628-7132"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pascale Fung","raw_affiliation_strings":["Human Language Technology Center, Electronic and Computer Engineering, University of Science and Technology (HKUST), Kowloon, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center, Electronic and Computer Engineering, University of Science and Technology (HKUST), Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103947452","display_name":"Lu Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lu Cao","raw_affiliation_strings":["Human Language Technology Center, Electronic and Computer Engineering, University of Science and Technology (HKUST), Kowloon, Hong Kong, China","University of Science and Technology (Hong Kong)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Human Language Technology Center, Electronic and Computer Engineering, University of Science and Technology (HKUST), Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"University of Science and Technology (Hong Kong)","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"467","last_page":"471"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9969000220298767,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.853981614112854},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.7368296384811401},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.7057335376739502},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6904455423355103},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6857830286026001},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.6493606567382812},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6309279203414917},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.483066588640213},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4751669764518738},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4536612927913666},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4214397370815277},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3362804055213928},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.2712496519088745},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10115090012550354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.853981614112854},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.7368296384811401},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7057335376739502},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6904455423355103},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6857830286026001},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.6493606567382812},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6309279203414917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.483066588640213},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4751669764518738},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4536612927913666},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4214397370815277},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3362804055213928},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2712496519088745},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10115090012550354},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/asru.2007.4430157","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2007.4430157","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE Workshop on Automatic Speech Recognition &amp; Understanding (ASRU)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.152.3816","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.152.3816","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ee.ust.hk/~pascale/Publications/conference/2007/ASRU2007-1.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-37475","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-37475","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W93383444","https://openalex.org/W163537071","https://openalex.org/W1505175215","https://openalex.org/W1631260214","https://openalex.org/W1637614433","https://openalex.org/W1651108041","https://openalex.org/W1822699154","https://openalex.org/W2002342963","https://openalex.org/W2100336732","https://openalex.org/W2100392285","https://openalex.org/W2100969003","https://openalex.org/W2145565331","https://openalex.org/W2163295968","https://openalex.org/W2188293537","https://openalex.org/W2402326842","https://openalex.org/W2964076070","https://openalex.org/W3144168424","https://openalex.org/W4285719527","https://openalex.org/W6606678367","https://openalex.org/W6630058488","https://openalex.org/W6636811518","https://openalex.org/W6636813098","https://openalex.org/W6687026376","https://openalex.org/W6712914314"],"related_works":["https://openalex.org/W2126322296","https://openalex.org/W2163537793","https://openalex.org/W4298261218","https://openalex.org/W3151376046","https://openalex.org/W4386794561","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W4388404911","https://openalex.org/W3021690593","https://openalex.org/W2105439218"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"our":[3,14,103,120,126],"work":[4,15],"on":[5,16],"mandarin":[6],"lecture":[7,58,73],"speech":[8,59,64,127],"transcription.":[9],"In":[10],"particular,":[11],"we":[12,114,124],"present":[13],"a":[17,108,131,136],"small":[18],"database,":[19],"which":[20],"contains":[21],"only":[22],"16":[23],"hours":[24],"of":[25,32,37,46,72,91,139],"audio":[26],"data":[27,60,65,82],"and":[28,50,69,78,98,134],"0.16":[29],"M":[30],"words":[31],"text":[33],"data.":[34],"A":[35],"range":[36],"experiments":[38],"have":[39],"been":[40],"done":[41],"to":[42,61],"improve":[43],"the":[44,47,51,57,62,70,89],"performances":[45],"acoustic":[48,67,95],"model":[49,96,100],"language":[52,84,99],"model,":[53],"these":[54],"include":[55],"adapting":[56],"reading":[63],"for":[66,83],"modeling":[68],"use":[71],"conference":[74],"paper,":[75],"power":[76],"points":[77],"similar":[79],"domain":[80],"web":[81],"modeling.":[85],"We":[86],"also":[87],"study":[88],"effects":[90],"automatic":[92],"segmentation,":[93],"unsupervised":[94],"adaptation":[97,101],"in":[102,119],"recognition":[104],"system.":[105,122],"By":[106],"using":[107],"3timesRT":[109],"multiple":[110],"passes":[111],"decoding":[112],"strategy,":[113],"obtain":[115,135],"70.3%":[116],"accuracy":[117],"performance":[118],"final":[121],"Finally,":[123],"apply":[125],"transcription":[128],"system":[129],"into":[130],"SVM":[132],"summarizer":[133],"ROUGE-L":[137],"F-measure":[138],"66.5%.":[140]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
