{"id":"https://openalex.org/W4372183461","doi":"https://doi.org/10.1109/icassp49357.2023.10094993","title":"Leveraging Large Text Corpora For End-To-End Speech Summarization","display_name":"Leveraging Large Text Corpora For End-To-End Speech Summarization","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372183461","doi":"https://doi.org/10.1109/icassp49357.2023.10094993"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10094993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5014468963","display_name":"Kohei Matsuura","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kohei Matsuura","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033975068","display_name":"Takanori Ashihara","orcid":"https://orcid.org/0009-0003-4322-4127"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takanori Ashihara","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087290011","display_name":"Takafumi Moriya","orcid":"https://orcid.org/0000-0003-1942-7250"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takafumi Moriya","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009756622","display_name":"Tomohiro Tanaka","orcid":"https://orcid.org/0000-0001-7442-4912"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Tanaka","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060644399","display_name":"Ryo Masumura","orcid":"https://orcid.org/0000-0002-2415-4149"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryo Masumura","raw_affiliation_strings":["NTT Corporation,Japan","NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"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":0.8738502264022827},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8186845779418945},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6605028510093689},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.562361478805542},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5431460738182068},{"id":"https://openalex.org/keywords/speech-translation","display_name":"Speech translation","score":0.49435877799987793},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.47369837760925293},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4424746334552765},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43114301562309265},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4241047501564026},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.42332905530929565},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4209470748901367},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3394007086753845},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.13170617818832397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8738502264022827},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8186845779418945},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6605028510093689},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.562361478805542},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5431460738182068},{"id":"https://openalex.org/C2780366754","wikidata":"https://www.wikidata.org/wiki/Q7494857","display_name":"Speech translation","level":3,"score":0.49435877799987793},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.47369837760925293},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4424746334552765},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43114301562309265},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4241047501564026},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.42332905530929565},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4209470748901367},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3394007086753845},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.13170617818832397}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10094993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10094993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1923455183","https://openalex.org/W2016269468","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2613904329","https://openalex.org/W2806237610","https://openalex.org/W2883586237","https://openalex.org/W2899274165","https://openalex.org/W2912937645","https://openalex.org/W2939558422","https://openalex.org/W2949615363","https://openalex.org/W2962965405","https://openalex.org/W2963581463","https://openalex.org/W2964012862","https://openalex.org/W2964161387","https://openalex.org/W2964243274","https://openalex.org/W2972388764","https://openalex.org/W2972818416","https://openalex.org/W2996403597","https://openalex.org/W3015280134","https://openalex.org/W3034999214","https://openalex.org/W3097632072","https://openalex.org/W3097777922","https://openalex.org/W3153127278","https://openalex.org/W3169905056","https://openalex.org/W3171639395","https://openalex.org/W3199259836","https://openalex.org/W3210527551","https://openalex.org/W4210327373","https://openalex.org/W4224925623","https://openalex.org/W4226291738","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6632455782","https://openalex.org/W6640255802","https://openalex.org/W6680111315","https://openalex.org/W6682631176","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6746700228","https://openalex.org/W6749894894","https://openalex.org/W6751643386","https://openalex.org/W6753186555","https://openalex.org/W6755559483","https://openalex.org/W6755639519","https://openalex.org/W6756200954","https://openalex.org/W6758673196","https://openalex.org/W6761205521","https://openalex.org/W6761447849","https://openalex.org/W6768009688","https://openalex.org/W6769311223","https://openalex.org/W6776336016","https://openalex.org/W6777337586","https://openalex.org/W6796464841","https://openalex.org/W6810502992"],"related_works":["https://openalex.org/W2990025607","https://openalex.org/W3045103338","https://openalex.org/W3007142233","https://openalex.org/W3037186962","https://openalex.org/W4385571610","https://openalex.org/W3177132412","https://openalex.org/W3198731777","https://openalex.org/W4200068392","https://openalex.org/W4362498905","https://openalex.org/W2338806053"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,23,59,138],"summarization":[2,28,93],"(E2E":[3],"SSum)":[4],"is":[5,33,62,67,102,114,126,190],"a":[6,52,72,87,105,127,166,171,205],"technique":[7,101],"to":[8,70,103,109,139,194,212],"directly":[9,131],"generate":[10,110],"summary":[11],"sentences":[12],"from":[13],"speech.":[14],"Compared":[15],"with":[16,120],"the":[17,30,46,64,121,140,157,184,191,209,214],"cascade":[18],"approach,":[19],"which":[20,113],"combines":[21],"automatic":[22],"recognition":[24],"(ASR)":[25],"and":[26,44,60,150],"text":[27,92,122],"models,":[29],"E2E":[31,74,96,117,141,200,219],"approach":[32],"more":[34,179],"promising":[35],"because":[36],"it":[37],"mitigates":[38],"ASR":[39],"errors,":[40],"incorporates":[41],"nonverbal":[42],"information,":[43],"simplifies":[45],"overall":[47],"system.":[48,76,221],"However,":[49],"since":[50],"collecting":[51],"large":[53,88,172],"amount":[54,89],"of":[55,90,136,178,186,208,216],"paired":[56],"data":[57,66,94],"(i.e.,":[58,174],"summary)":[61],"difficult,":[63],"training":[65,119],"usually":[68],"insufficient":[69],"train":[71],"robust":[73],"SSum":[75,97,118,142,220],"In":[77,160],"this":[78,189],"paper,":[79],"we":[80,203],"present":[81],"two":[82],"novel":[83],"methods":[84,152],"that":[85,130,146],"leverage":[86],"external":[91,196],"for":[95,116,199],"training.":[98],"The":[99,124],"first":[100,192],"utilize":[104],"text-to-speech":[106],"(TTS)":[107],"system":[108,164],"synthesized":[111,137],"speech,":[112],"used":[115],"summary.":[123],"second":[125],"TTS-free":[128],"method":[129],"inputs":[132],"phoneme":[133],"sequence":[134],"instead":[135],"model.":[143],"Experiments":[144],"show":[145],"our":[147,162,187,217],"proposed":[148,218],"TTS-":[149],"phoneme-based":[151],"improve":[153],"several":[154],"metrics":[155],"on":[156],"How2":[158,210],"dataset.":[159],"particular,":[161],"best":[163,185],"outperforms":[165],"previous":[167],"state-of-the-art":[168],"one":[169],"by":[170],"margin":[173],"METEOR":[175],"score":[176],"improvements":[177],"than":[180],"6":[181],"points).":[182],"To":[183],"knowledge,":[188],"work":[193],"use":[195],"language":[197],"resources":[198],"SSum.":[201],"Moreover,":[202],"report":[204],"detailed":[206],"analysis":[207],"dataset":[211],"confirm":[213],"validity":[215]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}