{"id":"https://openalex.org/W3007460537","doi":"https://doi.org/10.1109/asru46091.2019.9004023","title":"Syllable-Dependent Discriminative Learning for Small Footprint Text-Dependent Speaker Verification","display_name":"Syllable-Dependent Discriminative Learning for Small Footprint Text-Dependent Speaker Verification","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3007460537","doi":"https://doi.org/10.1109/asru46091.2019.9004023","mag":"3007460537"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9004023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004023","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5111291634","display_name":"Junyi Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junyi Peng","raw_affiliation_strings":["Peking University, Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I4210128628","display_name":"Peking University Shenzhen Hospital","ror":"https://ror.org/03kkjyb15","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210128628"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Peking University, Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I4210128628"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100368048","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-9545-3050"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Tencent, AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043757154","display_name":"Deyi Tuo","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deyi Tuo","raw_affiliation_strings":["Tencent, AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent, AI Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Tencent, AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100770786","display_name":"Meng Yu","orcid":"https://orcid.org/0000-0003-2554-2888"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Yu","raw_affiliation_strings":["Tencent, AI Lab, Bellevue, USA"],"affiliations":[{"raw_affiliation_string":"Tencent, AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458065","display_name":"Chunlei Zhang","orcid":"https://orcid.org/0000-0002-6253-2446"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunlei Zhang","raw_affiliation_strings":["Tencent, AI Lab, Bellevue, USA"],"affiliations":[{"raw_affiliation_string":"Tencent, AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent, AI Lab, Bellevue, USA"],"affiliations":[{"raw_affiliation_string":"Tencent, AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5111291634"],"corresponding_institution_ids":["https://openalex.org/I4210128628"],"apc_list":null,"apc_paid":null,"fwci":0.4201,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72745316,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"350","last_page":"357"},"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":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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/syllable","display_name":"Syllable","score":0.767366886138916},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7282363176345825},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6907978653907776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6418514847755432},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5780872106552124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4804201126098633},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4771658480167389},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4291667640209198},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36912673711776733}],"concepts":[{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.767366886138916},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7282363176345825},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6907978653907776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6418514847755432},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5780872106552124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4804201126098633},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4771658480167389},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4291667640209198},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36912673711776733},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9004023","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004023","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2046056978","https://openalex.org/W2064364374","https://openalex.org/W2114925438","https://openalex.org/W2129244720","https://openalex.org/W2150769028","https://openalex.org/W2187089797","https://openalex.org/W2402195372","https://openalex.org/W2407374891","https://openalex.org/W2584329820","https://openalex.org/W2612434969","https://openalex.org/W2747238065","https://openalex.org/W2748488820","https://openalex.org/W2802973008","https://openalex.org/W2900064592","https://openalex.org/W2900944893","https://openalex.org/W2937033898","https://openalex.org/W2949811029","https://openalex.org/W2962788625","https://openalex.org/W2962898354","https://openalex.org/W2962959915","https://openalex.org/W3012310164","https://openalex.org/W3099631870","https://openalex.org/W6713401928"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W2900413183","https://openalex.org/W147410782","https://openalex.org/W4287804464","https://openalex.org/W3022252430","https://openalex.org/W2965546495","https://openalex.org/W3103989898","https://openalex.org/W2152352598","https://openalex.org/W803346624"],"abstract_inverted_index":{"This":[0],"study":[1],"proposes":[2],"a":[3,37],"novel":[4,38],"scheme":[5,120],"of":[6,28],"syllable-dependent":[7,39,74],"discriminative":[8],"speaker":[9,16,96],"embedding":[10],"learning":[11],"for":[12],"small":[13],"footprint":[14],"text-dependent":[15],"verification":[17],"systems.":[18],"To":[19],"suppress":[20],"undesired":[21],"syllable":[22,51],"variation":[23],"and":[24,62,126],"enhance":[25],"the":[26,32,44,66,79,106,123,132],"power":[27],"discrimination":[29,100],"inherited":[30],"in":[31],"frame-level":[33,68,80],"features,":[34],"we":[35,71],"design":[36],"clustering":[40],"loss":[41,48],"to":[42,57,77,82,91],"optimize":[43],"network.":[45],"Specifically,":[46],"this":[47],"function":[49],"utilizes":[50],"labels":[52],"as":[53],"auxiliary":[54],"supervision":[55],"information":[56],"explicitly":[58],"maximize":[59],"inter-syllable":[60],"divisibility":[61],"intra-syllable":[63],"compactness":[64],"between":[65],"learned":[67],"features.":[69,108],"Successively,":[70],"propose":[72],"two":[73],"pooling":[75],"mechanisms":[76],"aggregate":[78],"features":[81,85,89],"several":[83],"syllable-level":[84,107],"by":[86,104],"averaging":[87],"those":[88],"corresponding":[90],"each":[92],"syllable.":[93],"The":[94],"utterance-level":[95],"embeddings":[97],"with":[98],"powerful":[99],"are":[101],"then":[102],"obtained":[103],"concatenating":[105],"Experimental":[109],"results":[110],"on":[111],"Tencent":[112],"voice":[113],"wake-up":[114],"dataset":[115],"show":[116],"that":[117],"our":[118],"proposed":[119],"can":[121],"accelerate":[122],"network":[124],"convergence":[125],"achieve":[127],"significant":[128],"performance":[129],"improvement":[130],"against":[131],"state-of-the-art":[133],"methods.":[134]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}