{"id":"https://openalex.org/W3152100107","doi":"https://doi.org/10.1109/slt48900.2021.9383583","title":"Convolution-Based Attention Model With Positional Encoding For Streaming Speech Recognition On Embedded Devices","display_name":"Convolution-Based Attention Model With Positional Encoding For Streaming Speech Recognition On Embedded Devices","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3152100107","doi":"https://doi.org/10.1109/slt48900.2021.9383583","mag":"3152100107"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5108758586","display_name":"Jin-Hwan Park","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinhwan Park","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100684422","display_name":"Chanwoo Kim","orcid":"https://orcid.org/0000-0003-0193-8167"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chanwoo Kim","raw_affiliation_strings":["Samsung Research, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Research, Seoul, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113491293","display_name":"Wonyong Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonyong Sung","raw_affiliation_strings":["Seoul National University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1464,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.34246603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"30","last_page":"37"},"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/T11309","display_name":"Music and Audio Processing","score":0.9958000183105469,"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/T10860","display_name":"Speech and Audio Processing","score":0.9947999715805054,"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":0.855831503868103},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.7712024450302124},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6527177691459656},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5907485485076904},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.576379656791687},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5681881308555603},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.5571230053901672},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5545512437820435},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5053730607032776},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4340208172798157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42384597659111023},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.42326849699020386},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.37654298543930054},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3373482823371887},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2215590476989746},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20465373992919922},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.18922916054725647}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.855831503868103},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.7712024450302124},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6527177691459656},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5907485485076904},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.576379656791687},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5681881308555603},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.5571230053901672},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5545512437820435},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5053730607032776},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4340208172798157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42384597659111023},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.42326849699020386},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.37654298543930054},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3373482823371887},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2215590476989746},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20465373992919922},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.18922916054725647},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383583","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383583","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6200000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W2064675550","https://openalex.org/W2127141656","https://openalex.org/W2143612262","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2251321385","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2577366047","https://openalex.org/W2605141709","https://openalex.org/W2606722458","https://openalex.org/W2613904329","https://openalex.org/W2631415506","https://openalex.org/W2745439869","https://openalex.org/W2750499125","https://openalex.org/W2754232744","https://openalex.org/W2767601419","https://openalex.org/W2936774411","https://openalex.org/W2952436057","https://openalex.org/W2962760690","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963037989","https://openalex.org/W2963174729","https://openalex.org/W2963312585","https://openalex.org/W2963414781","https://openalex.org/W2963738165","https://openalex.org/W2963827914","https://openalex.org/W2964121744","https://openalex.org/W2964199361","https://openalex.org/W2964265128","https://openalex.org/W2964272710","https://openalex.org/W2972451902","https://openalex.org/W2972630480","https://openalex.org/W2981857663","https://openalex.org/W2995426144","https://openalex.org/W3001899777","https://openalex.org/W3007528493","https://openalex.org/W3008191852","https://openalex.org/W3015281123","https://openalex.org/W3015974384","https://openalex.org/W3094759821","https://openalex.org/W3096104971","https://openalex.org/W4294619417","https://openalex.org/W4297779827","https://openalex.org/W4297818305","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6628973269","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6687566353","https://openalex.org/W6691770337","https://openalex.org/W6735706088","https://openalex.org/W6737778391","https://openalex.org/W6739901393","https://openalex.org/W6741807409","https://openalex.org/W6743440867","https://openalex.org/W6744720862","https://openalex.org/W6745543685","https://openalex.org/W6747158283","https://openalex.org/W6747270024","https://openalex.org/W6764398373","https://openalex.org/W6769557084","https://openalex.org/W6771497439","https://openalex.org/W6780226713"],"related_works":["https://openalex.org/W2109906613","https://openalex.org/W2384938095","https://openalex.org/W2097634141","https://openalex.org/W2394242538","https://openalex.org/W2073607182","https://openalex.org/W2000595727","https://openalex.org/W3125089330","https://openalex.org/W2097755885","https://openalex.org/W3005763386","https://openalex.org/W3013977768"],"abstract_inverted_index":{"On-device":[0],"automatic":[1],"speech":[2,151],"recognition":[3,152],"(ASR)":[4],"is":[5,65,105,116,126],"much":[6],"more":[7,72],"preferred":[8],"over":[9],"server-based":[10,21],"implementations":[11,48],"owing":[12],"to":[13,28,32,80,99],"its":[14],"low":[15],"latency":[16],"and":[17,133],"privacy":[18],"protection.":[19],"Many":[20],"ASRs":[22],"employ":[23],"recurrent":[24],"neural":[25],"networks":[26],"(RNNs)":[27],"exploit":[29],"their":[30],"ability":[31],"recognize":[33],"long":[34,78],"sequences":[35],"with":[36,61],"a":[37,55,77,100],"limited":[38],"number":[39],"of":[40,110,123,144],"states;":[41],"however,":[42],"they":[43,75],"are":[44],"inefficient":[45],"for":[46,148],"single-stream":[47],"in":[49],"embedded":[50],"devices.":[51],"In":[52,119],"this":[53,88],"study,":[54],"highly":[56],"efficient":[57,73],"convolutional":[58,114],"model-based":[59],"ASR":[60,102],"monotonic":[62],"chunkwise":[63],"attention":[64,131],"developed.":[66],"Although":[67],"temporal":[68],"convolution-based":[69,101],"models":[70],"allow":[71],"implementations,":[74],"demand":[76],"filter-length":[79,113],"avoid":[81],"looping":[82],"or":[83],"skipping":[84],"problems.":[85],"To":[86],"remedy":[87],"problem,":[89],"we":[90],"add":[91],"positional":[92,124],"encoding,":[93],"while":[94],"shortening":[95],"the":[96,108,111,121,130,140],"filter":[97],"length,":[98],"encoder.":[103],"It":[104],"demonstrated":[106],"that":[107],"accuracy":[109],"short":[112],"model":[115,138],"significantly":[117],"improved.":[118],"addition,":[120],"effect":[122],"encoding":[125],"analyzed":[127],"by":[128],"visualizing":[129],"energy":[132],"encoder":[134],"outputs.":[135],"The":[136],"proposed":[137],"achieves":[139],"word":[141],"error":[142],"rate":[143],"11.20%":[145],"on":[146],"TED-LIUMv2":[147],"an":[149],"end-to-end":[150],"task.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}