{"id":"https://openalex.org/W1735150698","doi":"https://doi.org/10.1109/icassp.2015.7178919","title":"Small-footprint high-performance deep neural network-based speech recognition using split-VQ","display_name":"Small-footprint high-performance deep neural network-based speech recognition using split-VQ","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1735150698","doi":"https://doi.org/10.1109/icassp.2015.7178919","mag":"1735150698"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100339989","display_name":"Yongqiang Wang","orcid":"https://orcid.org/0000-0002-8600-0276"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongqiang Wang","raw_affiliation_strings":["One Microsoft Way, Microsoft Corporation, Redmond, WA","Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["One Microsoft Way, Microsoft Corporation, Redmond, WA","Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101928537","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0002-3912-097X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["One Microsoft Way, Microsoft Corporation, Redmond, WA","Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"One Microsoft Way, Microsoft Corporation, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Corp., One Microsoft Way; Redmond, WA 98052 USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":5.3502,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.96664098,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"4984","last_page":"4988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9983000159263611,"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":0.9955000281333923,"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/codebook","display_name":"Codebook","score":0.7413387298583984},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7348405718803406},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6751622557640076},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6423662900924683},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5721887350082397},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5661932826042175},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5424677729606628},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5073394179344177},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.49688008427619934},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.48978257179260254},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.43382662534713745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42094850540161133},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34034815430641174}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.7413387298583984},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7348405718803406},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6751622557640076},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6423662900924683},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5721887350082397},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5661932826042175},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5424677729606628},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5073394179344177},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.49688008427619934},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.48978257179260254},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.43382662534713745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42094850540161133},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34034815430641174},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178919","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178919","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W587794757","https://openalex.org/W1634005169","https://openalex.org/W1984541135","https://openalex.org/W2034940213","https://openalex.org/W2046056978","https://openalex.org/W2058641082","https://openalex.org/W2084910356","https://openalex.org/W2095894002","https://openalex.org/W2096969571","https://openalex.org/W2112984492","https://openalex.org/W2134383396","https://openalex.org/W2142873456","https://openalex.org/W2145085734","https://openalex.org/W2147768505","https://openalex.org/W2156456363","https://openalex.org/W2160815625","https://openalex.org/W2294543795","https://openalex.org/W2296516251","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2396813586","https://openalex.org/W2402040300","https://openalex.org/W2403816900","https://openalex.org/W6617368339","https://openalex.org/W6683492994","https://openalex.org/W6696912008","https://openalex.org/W6697811694","https://openalex.org/W6712551501","https://openalex.org/W6712847557","https://openalex.org/W6713209763"],"related_works":["https://openalex.org/W2148772884","https://openalex.org/W2017514583","https://openalex.org/W2100120615","https://openalex.org/W2147406819","https://openalex.org/W2352648934","https://openalex.org/W1929869830","https://openalex.org/W2387054321","https://openalex.org/W2017401491","https://openalex.org/W2062765737","https://openalex.org/W2012827167"],"abstract_inverted_index":{"Due":[0],"to":[1,15,48,75,128,133],"a":[2,17,25,31,89,94,145,152,162],"large":[3,47],"number":[4,60],"of":[5,61,80,91,138],"parameters":[6],"in":[7,66,151],"deep":[8],"neural":[9],"networks":[10],"(DNNs),":[11],"it":[12],"is":[13,44,111],"challenging":[14],"design":[16],"small-footprint":[18],"DNN-based":[19],"speech":[20],"recognition":[21,27,158],"system":[22],"while":[23],"maintaining":[24],"high":[26],"performance.":[28],"Even":[29],"with":[30],"singular":[32],"value":[33],"matrix":[34],"decomposition":[35],"(SVD)":[36],"method":[37,119],"and":[38,85,130],"scalar":[39],"quantization,":[40],"the":[41,59,117,123],"DNN":[42,155,166],"model":[43,124],"still":[45],"too":[46],"be":[49,103],"deployed":[50],"on":[51,136],"many":[52],"mobile":[53],"devices.":[54],"Common":[55],"practices":[56],"like":[57],"reducing":[58],"hidden":[62],"nodes":[63],"often":[64],"result":[65],"significant":[67],"accuracy":[68],"loss.":[69],"In":[70],"this":[71],"work,":[72],"we":[73],"propose":[74],"split":[76,95],"each":[77],"row":[78],"vector":[79,96],"weight":[81],"matrices":[82],"into":[83,88],"sub-vectors,":[84],"quantize":[86],"them":[87],"set":[90],"codewords":[92],"using":[93,105],"quantization":[97,110],"(split-VQ)":[98],"algorithm.":[99],"The":[100],"codebook":[101],"can":[102,120,167],"fine-tuned":[104],"back-propagation":[106],"when":[107],"an":[108,139],"aggressive":[109],"performed.":[112],"Experimental":[113],"results":[114,150],"demonstrate":[115],"that":[116],"proposed":[118],"further":[121],"reduce":[122],"size":[125],"by":[126],"75%":[127],"80%":[129],"save":[131],"10%":[132],"50%":[134],"computation":[135],"top":[137],"already":[140],"very":[141],"compact":[142],"SVD-DNN":[143],"without":[144],"noticeable":[146],"performance":[147,159],"degradation.":[148],"This":[149],"3.2":[153],"MB-footprint":[154],"giving":[156],"similar":[157],"as":[160],"what":[161],"59.1":[163],"MB":[164],"standard":[165],"achieve.":[168]},"counts_by_year":[{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":11}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}