{"id":"https://openalex.org/W4224925623","doi":"https://doi.org/10.1109/icassp43922.2022.9747320","title":"End-to-End Speech Summarization Using Restricted Self-Attention","display_name":"End-to-End Speech Summarization Using Restricted Self-Attention","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224925623","doi":"https://doi.org/10.1109/icassp43922.2022.9747320"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747320","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/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, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036933477","display_name":"Shruti Palaskar","orcid":"https://orcid.org/0000-0001-8637-1897"},"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":"Shruti Palaskar","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107337645","display_name":"Alan W. Black","orcid":"https://orcid.org/0000-0001-8820-8831"},"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":"Alan W Black","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"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":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.409,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.999875,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995,"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":0.9995,"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":0.9995,"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":0.9995,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.4474683}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9551224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8687652},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6427573},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.63596946},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5546142},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.5261511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.52529246},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4474683},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4321453},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.365898},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747320","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.52,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":30,"referenced_works":["https://openalex.org/W2066350381","https://openalex.org/W2133459682","https://openalex.org/W2154652894","https://openalex.org/W2526425061","https://openalex.org/W2899274165","https://openalex.org/W2936695845","https://openalex.org/W2936774411","https://openalex.org/W2953104586","https://openalex.org/W2962780374","https://openalex.org/W2964110616","https://openalex.org/W2973127116","https://openalex.org/W2979826702","https://openalex.org/W3015468748","https://openalex.org/W3033529678","https://openalex.org/W3034999214","https://openalex.org/W3081312039","https://openalex.org/W3085629518","https://openalex.org/W3096471021","https://openalex.org/W3096798607","https://openalex.org/W3097777922","https://openalex.org/W3105238007","https://openalex.org/W3160360746","https://openalex.org/W3163463193","https://openalex.org/W3197898596","https://openalex.org/W3198084221","https://openalex.org/W3211495814","https://openalex.org/W4226291738","https://openalex.org/W4287704453","https://openalex.org/W4288024261","https://openalex.org/W4295838474"],"related_works":["https://openalex.org/W4385573810","https://openalex.org/W4362451017","https://openalex.org/W4317547544","https://openalex.org/W4316012698","https://openalex.org/W4313395829","https://openalex.org/W4308478176","https://openalex.org/W4288113047","https://openalex.org/W4221140906","https://openalex.org/W3098136301","https://openalex.org/W2947686949"],"abstract_inverted_index":{"Speech":[0],"summarization":[1,14,20,40],"is":[2,22],"typically":[3],"performed":[4],"by":[5,118,149],"using":[6],"a":[7,63],"cascade":[8,147],"of":[9,18,48,105,132],"speech":[10,19,69,81,100,136],"recognition":[11],"and":[12,27,87,138],"text":[13],"models.":[15],"End-to-end":[16],"modeling":[17],"models":[21,53,79,82],"challenging":[23],"due":[24],"to":[25,44,54,80,83,97],"memory":[26,86],"compute":[28,88],"constraints":[29],"arising":[30],"from":[31,77,135],"long":[32,56],"input":[33],"audio":[34],"sequences.":[35,57],"Recent":[36],"work":[37],"in":[38],"document":[39],"has":[41],"inspired":[42],"methods":[43],"reduce":[45],"the":[46,73,85,93,102,113,127,141,146],"complexity":[47],"self-attentions,":[49],"which":[50],"enables":[51],"transformer":[52],"handle":[55],"In":[58],"this":[59],"work,":[60],"we":[61,125],"introduce":[62],"single":[64],"model":[65,95,111,117,144,148],"optimized":[66],"end-to-end":[67,110,143],"for":[68,101],"summarization.":[70],"We":[71,90],"apply":[72],"restricted":[74],"self-attention":[75],"technique":[76],"text-based":[78],"address":[84],"constraints.":[89],"demonstrate":[91],"that":[92,140],"proposed":[94,109,115,142],"learns":[96],"directly":[98],"summarize":[99],"How-2":[103],"corpus":[104],"instructional":[106],"videos.":[107],"The":[108],"outperforms":[112,145],"previously":[114],"cascaded":[116],"3":[119],"points":[120,151],"absolute":[121,152],"on":[122],"ROUGE.":[123],"Further,":[124],"consider":[126],"spoken":[128],"language":[129],"understanding":[130],"task":[131],"predicting":[133],"concepts":[134],"inputs":[137],"show":[139],"4":[150],"F-1.":[153]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4224925623","counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":3}],"updated_date":"2024-12-09T12:56:04.121732","created_date":"2022-04-28"}