{"id":"https://openalex.org/W2767433836","doi":"https://doi.org/10.1109/icdsp.2017.8096138","title":"Enhancing speaker verification with short voice commands via autoencoder and phonetic bottleneck learning","display_name":"Enhancing speaker verification with short voice commands via autoencoder and phonetic bottleneck learning","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2767433836","doi":"https://doi.org/10.1109/icdsp.2017.8096138","mag":"2767433836"},"language":"en","primary_location":{"id":"doi:10.1109/icdsp.2017.8096138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2017.8096138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 22nd International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"},"type":"article","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/A5104229637","display_name":"Yi\u2010Chi Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yichi Huang","raw_affiliation_strings":["ADSPLab/ELIP/Shenzhen Key Laboratory for IMVR School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"ADSPLab/ELIP/Shenzhen Key Laboratory for IMVR School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["ADSPLab/ELIP/Shenzhen Key Laboratory for IMVR School of ECE, Peking University, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"ADSPLab/ELIP/Shenzhen Key Laboratory for IMVR School of ECE, Peking University, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5104229637"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15026814,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9990000128746033,"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":0.9965000152587891,"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/bottleneck","display_name":"Bottleneck","score":0.8645691871643066},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.853602409362793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8293909430503845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7344274520874023},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6190404295921326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.550180196762085},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5403661131858826},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5051899552345276},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48985621333122253},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4424671232700348},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4120349586009979},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1262601912021637}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8645691871643066},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.853602409362793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8293909430503845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7344274520874023},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6190404295921326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.550180196762085},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5403661131858826},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5051899552345276},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48985621333122253},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4424671232700348},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4120349586009979},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1262601912021637},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdsp.2017.8096138","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdsp.2017.8096138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 22nd International Conference on Digital Signal Processing (DSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7699999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320329791","display_name":"Shenzhen Fundamental Research Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1528954144","https://openalex.org/W1996512145","https://openalex.org/W2025768430","https://openalex.org/W2096653978","https://openalex.org/W2101578820","https://openalex.org/W2121812409","https://openalex.org/W2145094598","https://openalex.org/W2145846419","https://openalex.org/W2150769028","https://openalex.org/W2295119550","https://openalex.org/W2405774341","https://openalex.org/W2407127962","https://openalex.org/W2514700786","https://openalex.org/W2997574889","https://openalex.org/W6631362777","https://openalex.org/W6681096077"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W2669956259","https://openalex.org/W4249005693","https://openalex.org/W4392946183","https://openalex.org/W3088732000"],"abstract_inverted_index":{"Deep":[0],"learning":[1,94],"based":[2,95],"speaker":[3],"verification":[4],"methods":[5],"(SV)":[6],"have":[7,115],"achieved":[8],"the":[9,47,68,77,88,119],"state-of-the-art":[10],"performance.":[11],"However,":[12],"SV":[13,131],"with":[14,87,118],"short":[15,49],"voice":[16],"commands":[17],"(SV-SVC)":[18],"is":[19,46,58,98],"still":[20],"challenging":[21],"and":[22,56,105],"its":[23],"performance":[24],"degrades":[25],"significantly":[26],"when":[27],"noise":[28,74],"presents.":[29],"Carefully":[30],"examining":[31],"of":[32,70,102],"SV-SVC":[33,96],"task":[34],"in":[35,72],"real":[36],"applications":[37],"reveals":[38],"that":[39],"there":[40],"are":[41],"two":[42],"unavoidable":[43],"limitations.":[44],"One":[45],"very":[48],"utterances":[50],"used":[51],"(less":[52],"than":[53],"1":[54],"second)":[55],"another":[57],"dynamically":[59],"changing":[60],"ambient":[61],"noise.":[62],"In":[63],"this":[64],"study,":[65],"encouraged":[66],"by":[67],"capability":[69],"autoencoder":[71,104],"handling":[73],"suppression":[75],"meanwhile":[76],"optimized":[78],"phonetic":[79,106],"bottleneck":[80,107],"features":[81],"holding":[82],"some":[83],"contextual":[84],"information":[85],"learned":[86],"training":[89],"data,":[90],"a":[91],"novel":[92],"deep":[93],"architecture":[97],"developed":[99],"which":[100],"consists":[101],"an":[103],"neural":[108],"network":[109],"for":[110],"feature":[111],"learning.":[112],"Extensive":[113],"experiments":[114],"been":[116],"conducted":[117],"public":[120],"database":[121],"RSR2015.":[122],"Results":[123],"validate":[124],"our":[125],"proposed":[126],"method":[127],"outperforming":[128],"the-state-of-the-art":[129],"i-vector":[130],"system.":[132]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}