{"id":"https://openalex.org/W3015923889","doi":"https://doi.org/10.1109/icassp40776.2020.9053998","title":"Speaker-Aware Training of Attention-Based End-to-End Speech Recognition Using Neural Speaker Embeddings","display_name":"Speaker-Aware Training of Attention-Based End-to-End Speech Recognition Using Neural Speaker Embeddings","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015923889","doi":"https://doi.org/10.1109/icassp40776.2020.9053998","mag":"3015923889"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/en/publications/17b37434-aaee-43d8-9718-888409b279c4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045737992","display_name":"Aku Rouhe","orcid":"https://orcid.org/0009-0000-0977-609X"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Aku Rouhe","raw_affiliation_strings":["Aalto University,Department of Signal processing and acoustics","Department of Signal processing and acoustics, Aalto University"],"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal processing and acoustics","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal processing and acoustics, Aalto University","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034616922","display_name":"Tuomas Kaseva","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Tuomas Kaseva","raw_affiliation_strings":["Aalto University,Department of Signal processing and acoustics","Department of Signal processing and acoustics, Aalto University"],"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal processing and acoustics","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal processing and acoustics, Aalto University","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":["Aalto University,Department of Signal processing and acoustics","Department of Signal processing and acoustics, Aalto University"],"affiliations":[{"raw_affiliation_string":"Aalto University,Department of Signal processing and acoustics","institution_ids":["https://openalex.org/I9927081"]},{"raw_affiliation_string":"Department of Signal processing and acoustics, Aalto University","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5045737992"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.4139,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.68653079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7064","last_page":"7068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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/T11309","display_name":"Music and Audio Processing","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.8081755638122559},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7979758977890015},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7774776220321655},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7499877214431763},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6717296838760376},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6021814942359924},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5864657163619995},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5366788506507874},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5062150359153748},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.48397040367126465},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4839380383491516},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.438601553440094},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36327072978019714}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.8081755638122559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7979758977890015},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7774776220321655},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7499877214431763},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6717296838760376},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6021814942359924},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5864657163619995},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5366788506507874},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5062150359153748},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.48397040367126465},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4839380383491516},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.438601553440094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36327072978019714}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053998","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053998","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/46322","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/17b37434-aaee-43d8-9718-888409b279c4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/46322","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/17b37434-aaee-43d8-9718-888409b279c4","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1936725236","https://openalex.org/W2024490156","https://openalex.org/W2079623482","https://openalex.org/W2146635662","https://openalex.org/W2150769028","https://openalex.org/W2251321385","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2597757402","https://openalex.org/W2726515241","https://openalex.org/W2805745502","https://openalex.org/W2808631503","https://openalex.org/W2889282842","https://openalex.org/W2889374926","https://openalex.org/W2890964092","https://openalex.org/W2916104401","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963240019","https://openalex.org/W2963381607","https://openalex.org/W2972403660","https://openalex.org/W2972621414","https://openalex.org/W3007327651","https://openalex.org/W3008391559","https://openalex.org/W4235169531","https://openalex.org/W6631362777","https://openalex.org/W6691770337","https://openalex.org/W6752334204"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W1521299571","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W2972909277","https://openalex.org/W1493012537","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"In":[0],"speaker-aware":[1,27,48],"training,":[2],"a":[3,41,51,87],"speaker":[4,24,57],"embedding":[5,62,104],"is":[6],"appended":[7],"to":[8,16,23,29,54],"DNN":[9,15],"input":[10],"features.":[11],"This":[12],"allows":[13],"the":[14,81,96],"effectively":[17],"learn":[18],"representations,":[19],"which":[20],"are":[21],"robust":[22],"variability.We":[25],"apply":[26,60],"training":[28,49],"attention-based":[30],"end-to-end":[31,43],"speech":[32],"recognition.":[33],"We":[34,45,72,91],"show":[35],"that":[36],"it":[37],"can":[38],"improve":[39],"over":[40],"purely":[42],"baseline.":[44],"also":[46],"propose":[47],"as":[50,70],"viable":[52],"method":[53],"leverage":[55],"untranscribed,":[56],"annotated":[58],"data.We":[59],"state-of-the-art":[61],"approaches,":[63],"both":[64],"i-vectors":[65],"and":[66,85,98],"neural":[67,113],"embeddings,":[68],"such":[69],"x-vectors.":[71],"experiment":[73],"with":[74],"embeddings":[75,114],"trained":[76],"in":[77,110],"two":[78],"conditions:":[79],"on":[80,86,95],"fixed":[82],"ASR":[83],"data,":[84],"large":[88],"untranscribed":[89],"dataset.":[90],"run":[92],"our":[93],"experiments":[94],"TED-LIUM":[97],"Wall":[99],"Street":[100],"Journal":[101],"datasets.":[102],"No":[103],"consistently":[105],"outperforms":[106],"all":[107],"others,":[108],"but":[109],"many":[111],"settings":[112],"outperform":[115],"i-vectors.":[116]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}