{"id":"https://openalex.org/W3096888553","doi":"https://doi.org/10.21437/interspeech.2020-2079","title":"Streaming Transformer-Based Acoustic Models Using Self-Attention with Augmented Memory","display_name":"Streaming Transformer-Based Acoustic Models Using Self-Attention with Augmented Memory","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096888553","doi":"https://doi.org/10.21437/interspeech.2020-2079","mag":"3096888553"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2079","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","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/A5101579713","display_name":"Chunyang Wu","orcid":"https://orcid.org/0000-0002-0269-3555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunyang Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100339989","display_name":"Yongqiang Wang","orcid":"https://orcid.org/0000-0002-8600-0276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yongqiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103247973","display_name":"Yangyang Shi","orcid":"https://orcid.org/0000-0001-5297-4155"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangyang Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087421101","display_name":"Ching-Feng Yeh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ching-Feng Yeh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101984914","display_name":"Frank Zhang","orcid":"https://orcid.org/0000-0001-9946-6502"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2899,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.96625845,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2132","last_page":"2136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.6940823793411255},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.684005618095398},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3603116571903229},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.2046320140361786},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10338810086250305},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10201427340507507}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6940823793411255},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.684005618095398},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3603116571903229},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2046320140361786},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10338810086250305},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10201427340507507}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-2079","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2079","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1686810756","https://openalex.org/W2184045248","https://openalex.org/W2288502450","https://openalex.org/W2293634267","https://openalex.org/W2329068866","https://openalex.org/W2407080277","https://openalex.org/W2729190387","https://openalex.org/W2802023636","https://openalex.org/W2896457183","https://openalex.org/W2913718171","https://openalex.org/W2936774411","https://openalex.org/W2941814890","https://openalex.org/W2944255943","https://openalex.org/W2962760690","https://openalex.org/W2962826786","https://openalex.org/W2964084166","https://openalex.org/W2964110616","https://openalex.org/W2972818416","https://openalex.org/W2981857663","https://openalex.org/W2992696780","https://openalex.org/W3007433671","https://openalex.org/W3008525923","https://openalex.org/W3015960524","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3097075707","https://openalex.org/W4288024261","https://openalex.org/W4288088457","https://openalex.org/W4288400010","https://openalex.org/W4303633609","https://openalex.org/W4385245566","https://openalex.org/W4394666973"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Transformer-based":[0],"acoustic":[1],"modeling":[2],"has":[3],"achieved":[4,94],"great":[5],"success":[6],"for":[7,38,71],"both":[8],"hybrid":[9],"and":[10,21,60,93],"sequence-to-sequence":[11],"speech":[12],"recognition.However,":[13],"it":[14],"requires":[15],"access":[16],"to":[17,29],"the":[18,22,30,57,68,73,76,84,102],"full":[19],"sequence,":[20],"computational":[23],"cost":[24],"grows":[25],"quadratically":[26],"with":[27,101],"respect":[28],"input":[31,58],"sequence":[32,59],"length.These":[33],"factors":[34],"limit":[35],"its":[36],"adoption":[37],"streaming":[39],"applications.In":[40],"this":[41],"work,":[42],"we":[43],"proposed":[44,80],"a":[45,53,61,90],"novel":[46],"augmented":[47],"memory":[48,65],"self-attention,":[49],"which":[50],"attends":[51],"on":[52,111],"short":[54],"segment":[55],"of":[56,63],"bank":[62,66],"memories.The":[64],"stores":[67],"embedding":[69],"information":[70],"all":[72,83],"processed":[74],"segments.On":[75],"librispeech":[77],"benchmark,":[78],"our":[79],"method":[81],"outperforms":[82],"existing":[85],"streamable":[86],"transformer":[87],"methods":[88],"by":[89],"large":[91,113],"margin":[92],"over":[95],"15%":[96],"relative":[97],"error":[98],"reduction,":[99],"compared":[100],"widely":[103],"used":[104],"LC-BLSTM":[105],"baseline.Our":[106],"findings":[107],"are":[108],"also":[109],"confirmed":[110],"some":[112],"internal":[114],"datasets.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":11},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}