{"id":"https://openalex.org/W4372269220","doi":"https://doi.org/10.1109/icassp49357.2023.10095019","title":"Speech Summarization of Long Spoken Document: Improving Memory Efficiency of Speech/Text Encoders","display_name":"Speech Summarization of Long Spoken Document: Improving Memory Efficiency of Speech/Text Encoders","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372269220","doi":"https://doi.org/10.1109/icassp49357.2023.10095019"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095019","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/A5042592085","display_name":"Takatomo Kano","orcid":"https://orcid.org/0000-0001-9693-3785"},"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":"Takatomo Kano","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":"middle","author":{"id":"https://openalex.org/A5056041031","display_name":"Roshan Sharma","orcid":"https://orcid.org/0000-0001-9886-009X"},"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":"Roshan Sharma","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,USA","Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","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":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"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":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,Pittsburgh,USA","Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"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/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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":0.9990000128746033,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9988999962806702,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9010705947875977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8847675919532776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6778692007064819},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.5844870805740356},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5552970170974731},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5070617198944092},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4985780715942383},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47763529419898987},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4593390226364136},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.45891013741493225},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4438363015651703},{"id":"https://openalex.org/keywords/spoken-language","display_name":"Spoken language","score":0.4393789768218994},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4203028380870819},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.39892956614494324}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9010705947875977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8847675919532776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6778692007064819},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.5844870805740356},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5552970170974731},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5070617198944092},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4985780715942383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47763529419898987},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4593390226364136},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.45891013741493225},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4438363015651703},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.4393789768218994},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4203028380870819},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.39892956614494324},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095019","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095019","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":[{"display_name":"Quality Education","score":0.550000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W71960489","https://openalex.org/W2064675550","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2163605009","https://openalex.org/W2584992898","https://openalex.org/W2792643794","https://openalex.org/W2886381447","https://openalex.org/W2896457183","https://openalex.org/W2899274165","https://openalex.org/W2949530332","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2972818416","https://openalex.org/W3015468748","https://openalex.org/W3081352735","https://openalex.org/W3097777922","https://openalex.org/W3114026450","https://openalex.org/W3143377973","https://openalex.org/W3162090017","https://openalex.org/W3163793923","https://openalex.org/W3177318507","https://openalex.org/W3209494353","https://openalex.org/W4224925623","https://openalex.org/W4225315575","https://openalex.org/W4226291738","https://openalex.org/W4287704453","https://openalex.org/W4385245566","https://openalex.org/W6682631176","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6749029207","https://openalex.org/W6755207826","https://openalex.org/W6755559483","https://openalex.org/W6768009688","https://openalex.org/W6776048684","https://openalex.org/W6778960353","https://openalex.org/W6781533629","https://openalex.org/W6782625385","https://openalex.org/W6796707148","https://openalex.org/W6803136910"],"related_works":["https://openalex.org/W2401827384","https://openalex.org/W2184127972","https://openalex.org/W642007152","https://openalex.org/W2550171623","https://openalex.org/W2343205865","https://openalex.org/W2008120082","https://openalex.org/W2810519502","https://openalex.org/W2341426843","https://openalex.org/W2131711534","https://openalex.org/W2187296505"],"abstract_inverted_index":{"Speech":[0],"summarization":[1,31,88,105,110,177],"requires":[2,89],"processing":[3],"several":[4],"minute-long":[5,144],"speech":[6,26,51,87,99,104,145],"sequences":[7,146],"to":[8,39,68,96,122,124,162,195],"allow":[9],"exploiting":[10,200],"the":[11,34,43,79,116,119,128,137,150,164,183,187,201],"whole":[12],"context":[13],"of":[14,24,82,118,130,140,171],"a":[15,22,103,172],"spoken":[16,203],"document.":[17],"A":[18],"conventional":[19,120,151],"approach":[20],"is":[21,115,147],"cascade":[23,35,44,83],"automatic":[25],"recognition":[27],"(ASR)":[28],"and":[29,52],"text":[30,157],"(TS).":[32],"However,":[33,85,136],"systems":[36,75],"are":[37],"sensitive":[38],"ASR":[40,80,160],"errors.":[41],"Moreover,":[42],"system":[45,106,169,189],"cannot":[46],"be":[47],"optimized":[48,67],"for":[49,143],"input":[50],"utilize":[53],"para-linguistic":[54],"information.":[55],"Recently,":[56],"there":[57],"has":[58],"been":[59],"an":[60],"increased":[61],"interest":[62],"in":[63],"end-to-end":[64],"(E2E)":[65],"approaches":[66],"output":[69],"summaries":[70],"directly":[71],"from":[72,111,159],"speech.":[73],"Such":[74],"can":[76],"thus":[77,154],"mitigate":[78],"errors":[81],"approaches.":[84],"E2E":[86,109],"massive":[90],"computational":[91],"resources":[92],"because":[93],"it":[94],"needs":[95],"encode":[97],"long":[98,202],"sequences.":[100],"We":[101,153,179],"propose":[102],"that":[107],"enables":[108],"100":[112],"seconds,":[113],"which":[114],"limit":[117],"method,":[121],"up":[123,194],"10":[125],"minutes":[126],"(i.e.,":[127],"duration":[129],"typical":[131],"instructional":[132],"videos":[133],"on":[134,182],"YouTube).":[135],"modeling":[138,165],"capability":[139],"this":[141],"model":[142],"weaker":[148],"than":[149],"approach.":[152],"exploit":[155],"auxiliary":[156],"information":[158],"transcriptions":[161],"improve":[163],"capabilities.":[166],"The":[167],"resultant":[168],"consists":[170],"dual":[173],"speech/text":[174],"encoder":[175],"decoder-based":[176],"system.":[178],"perform":[180],"experiments":[181],"How2":[184],"dataset":[185],"showing":[186],"proposed":[188],"improved":[190],"METEOR":[191],"scores":[192],"by":[193,198],"2.7":[196],"points":[197],"fully":[199],"documents.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}