{"id":"https://openalex.org/W7130535869","doi":"https://doi.org/10.1109/apccas67402.2025.11378307","title":"ECHO: An Efficient Co-Designed ASR Accelerator with Hardware-Friendly and Audio-Aware Attention","display_name":"ECHO: An Efficient Co-Designed ASR Accelerator with Hardware-Friendly and Audio-Aware Attention","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W7130535869","doi":"https://doi.org/10.1109/apccas67402.2025.11378307"},"language":null,"primary_location":{"id":"doi:10.1109/apccas67402.2025.11378307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas67402.2025.11378307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","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/A5012454941","display_name":"T. Y. Li","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tseng-Jen Li","raw_affiliation_strings":["Institute of Electronics, National Yang Ming Chiao Tung University,Hsinchu,Taiwan,300093"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronics, National Yang Ming Chiao Tung University,Hsinchu,Taiwan,300093","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067793643","display_name":"Tian\u2010Sheuan Chang","orcid":"https://orcid.org/0000-0002-0561-8745"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tian-Sheuan Chang","raw_affiliation_strings":["Institute of Electronics, National Yang Ming Chiao Tung University,Hsinchu,Taiwan,300093"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Electronics, National Yang Ming Chiao Tung University,Hsinchu,Taiwan,300093","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8759999871253967,"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":0.8759999871253967,"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":0.05689999833703041,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.009800000116229057,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5720999836921692},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5212000012397766},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5123000144958496},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4999000132083893},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.49790000915527344},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47269999980926514},{"id":"https://openalex.org/keywords/diagonal","display_name":"Diagonal","score":0.4366999864578247},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.42590001225471497},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4025000035762787}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531999945640564},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5720999836921692},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5486000180244446},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5212000012397766},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5123000144958496},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4999000132083893},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47269999980926514},{"id":"https://openalex.org/C130367717","wikidata":"https://www.wikidata.org/wiki/Q189791","display_name":"Diagonal","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.42590001225471497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4108000099658966},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4025000035762787},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C2777675136","wikidata":"https://www.wikidata.org/wiki/Q835642","display_name":"TOPS","level":3,"score":0.32280001044273376},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C2385561","wikidata":"https://www.wikidata.org/wiki/Q45432","display_name":"RSS","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apccas67402.2025.11378307","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apccas67402.2025.11378307","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Asia Pacific Conference on Circuits and Systems (APCCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.9156891107559204,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W3017024317","https://openalex.org/W3096017728","https://openalex.org/W3105238007","https://openalex.org/W3159727696","https://openalex.org/W3189877953","https://openalex.org/W3205192296","https://openalex.org/W4214686755","https://openalex.org/W4285309026","https://openalex.org/W4380881077","https://openalex.org/W4396909834","https://openalex.org/W4404954358","https://openalex.org/W4408174495","https://openalex.org/W4411727245"],"related_works":[],"abstract_inverted_index":{"Transformer-based":[0],"speech":[1,26,36,129],"models":[2],"offer":[3],"high":[4],"accuracy":[5,68,110],"but":[6],"suffer":[7],"from":[8],"heavy":[9],"computational":[10],"and":[11,62,80],"memory":[12],"costs,":[13],"hindering":[14],"their":[15],"deployment":[16],"on":[17,112,132],"edge":[18,133],"devices.":[19],"This":[20],"paper":[21],"presents":[22],"ECHO,":[23],"an":[24,31],"efficient":[25],"processing":[27,78],"accelerator":[28,73],"that":[29],"integrates":[30],"Audio-Aware":[32],"Attention":[33,57,66],"tailored":[34],"to":[35,58,105],"tasks.":[37],"ECHO's":[38],"optimized":[39],"attention":[40,102],"comprises":[41],"(1)":[42],"Signed":[43],"Bit":[44],"Fast":[45],"Prediction":[46],"for":[47,67,84,115,128],"low-cost":[48],"identification":[49],"of":[50,92,101],"TOP-P":[51],"vertical":[52],"attention,":[53],"(2)":[54],"Sliding":[55],"Diagonal":[56],"capture":[59],"diagonal":[60],"patterns,":[61],"(3)":[63],"Selective":[64],"Vertical":[65],"refinement-all":[69],"without":[70],"retraining.":[71],"The":[72],"features":[74],"a":[75,81,125],"reconfigurable":[76],"mixed-precision":[77],"element":[79],"sparsity-aware":[82],"dataflow":[83],"energy-efficient":[85],"execution.":[86],"ECHO":[87,117],"achieves":[88],"the":[89],"peak":[90],"performance":[91],"35.85":[93],"TOPS":[94],"at":[95],"180.07":[96],"TOPS/W,":[97],"while":[98],"reducing":[99],"computation":[100],"by":[103],"up":[104],"83.3%":[106],"with":[107],"only":[108],"0.21%":[109],"loss":[111],"wav2vec":[113],"2.0":[114],"LibriSpeech.":[116],"outperforms":[118],"prior":[119],"accelerators":[120],"in":[121],"energy":[122],"efficiency,":[123],"establishing":[124],"strong":[126],"benchmark":[127],"transformer":[130],"inference":[131],"platforms.":[134]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-20T00:00:00"}