{"id":"https://openalex.org/W2977456144","doi":"https://doi.org/10.1587/transinf.2019edl8023","title":"Vector Quantization of High-Dimensional Speech Spectra Using Deep Neural Network","display_name":"Vector Quantization of High-Dimensional Speech Spectra Using Deep Neural Network","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2977456144","doi":"https://doi.org/10.1587/transinf.2019edl8023","mag":"2977456144"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2019edl8023","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edl8023","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/10/E102.D_2019EDL8023/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/10/E102.D_2019EDL8023/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101826688","display_name":"Jianfeng Wu","orcid":"https://orcid.org/0000-0001-8105-7284"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"JianFeng WU","raw_affiliation_strings":["The Institute of Electron Device and Application, Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Electron Device and Application, Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103107764","display_name":"Huibin Qin","orcid":"https://orcid.org/0000-0001-6848-1291"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"HuiBin QIN","raw_affiliation_strings":["The Institute of Electron Device and Application, Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Electron Device and Application, Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009537627","display_name":"Yongzhu Hua","orcid":"https://orcid.org/0000-0001-6291-3866"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"YongZhu HUA","raw_affiliation_strings":["The Institute of Electron Device and Application, Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Electron Device and Application, Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002112296","display_name":"Lihuan Shao","orcid":"https://orcid.org/0009-0006-2130-6297"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"LiHuan SHAO","raw_affiliation_strings":["The Institute of Electron Device and Application, Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Electron Device and Application, Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103187153","display_name":"Ji Hu","orcid":"https://orcid.org/0000-0002-1806-6070"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji HU","raw_affiliation_strings":["The Institute of Electron Device and Application, Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Electron Device and Application, Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058235577","display_name":"Shengying Yang","orcid":"https://orcid.org/0000-0003-3010-1622"},"institutions":[{"id":"https://openalex.org/I50760025","display_name":"Hangzhou Dianzi University","ror":"https://ror.org/0576gt767","country_code":"CN","type":"education","lineage":["https://openalex.org/I50760025"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ShengYing YANG","raw_affiliation_strings":["The Institute of Electron Device and Application, Hangzhou Dianzi University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Institute of Electron Device and Application, Hangzhou Dianzi University","institution_ids":["https://openalex.org/I50760025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I50760025"],"apc_list":null,"apc_paid":null,"fwci":0.0993,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.4398836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"E102.D","issue":"10","first_page":"2047","last_page":"2050"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.8448121547698975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7341263890266418},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.669815719127655},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6128222942352295},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5994858145713806},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5785514116287231},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5467764139175415},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4760451316833496},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4704885482788086},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4642311930656433},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4545922875404358},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.43361255526542664},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4141066074371338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37872159481048584},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1834000051021576},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.15934255719184875}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.8448121547698975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7341263890266418},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.669815719127655},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6128222942352295},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5994858145713806},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5785514116287231},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5467764139175415},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4760451316833496},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4704885482788086},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4642311930656433},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4545922875404358},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43361255526542664},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4141066074371338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37872159481048584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1834000051021576},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.15934255719184875},{"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/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2019edl8023","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edl8023","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/10/E102.D_2019EDL8023/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2019edl8023","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2019edl8023","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E102.D/10/E102.D_2019EDL8023/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2977456144.pdf","grobid_xml":"https://content.openalex.org/works/W2977456144.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W2100495367","https://openalex.org/W2108665656","https://openalex.org/W2127218421","https://openalex.org/W2134383396","https://openalex.org/W2136922672","https://openalex.org/W2168013545","https://openalex.org/W2396976214","https://openalex.org/W2913932916","https://openalex.org/W4231109964","https://openalex.org/W4244017338"],"related_works":["https://openalex.org/W3016109656","https://openalex.org/W2058482658","https://openalex.org/W1973895194","https://openalex.org/W3135613579","https://openalex.org/W4386746628","https://openalex.org/W1980687383","https://openalex.org/W2166831097","https://openalex.org/W2546593254","https://openalex.org/W3209446892","https://openalex.org/W2792294082"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,85],"deep":[4],"neural":[5],"network":[6],"(DNN)":[7],"based":[8],"framework":[9,133],"to":[10,27,31,65,80,89],"address":[11,52],"the":[12,33,38,41,44,66,69,74,77,90,111,117,130,145],"problem":[13],"of":[14,24,37,43,68,76,110,138,147],"vector":[15],"quantization":[16],"(VQ)":[17],"for":[18,115,122],"high-dimensional":[19],"data.":[20],"The":[21,105],"main":[22],"challenge":[23],"applying":[25],"DNN":[26],"VQ":[28,132,149],"is":[29,47,113,142],"how":[30],"reduce":[32],"binary":[34],"coding":[35,45,70,78,118],"error":[36],"auto-encoder":[39],"when":[40],"distribution":[42],"units":[46],"far":[48,143],"from":[49],"binary.":[50],"To":[51],"this":[53],"problem,":[54],"three":[55],"fine-tuning":[56,94],"methods":[57,95,112],"have":[58,96],"been":[59,97],"adopted:":[60],"1)":[61],"adding":[62,84],"Gaussian":[63],"noise":[64],"input":[67],"layer,":[71],"2)":[72],"forcing":[73],"output":[75],"layer":[79],"be":[81],"binary,":[82],"3)":[83],"non-binary":[86],"penalty":[87],"term":[88],"loss":[91],"function.":[92],"These":[93],"extensively":[98],"evaluated":[99],"on":[100],"quantizing":[101,123],"speech":[102,125],"magnitude":[103],"spectra.":[104],"results":[106],"demonstrated":[107],"that":[108],"each":[109],"useful":[114],"improving":[116],"performance.":[119],"When":[120],"implemented":[121],"968-dimensional":[124],"spectra":[126],"using":[127],"only":[128],"18-bit,":[129],"DNN-based":[131],"achieved":[134],"an":[135],"averaged":[136],"PESQ":[137],"about":[139],"2.09,":[140],"which":[141],"beyond":[144],"capability":[146],"conventional":[148],"methods.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}