{"id":"https://openalex.org/W2963300763","doi":"https://doi.org/10.1109/iscslp.2016.7918381","title":"Binary speaker embedding","display_name":"Binary speaker embedding","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W2963300763","doi":"https://doi.org/10.1109/iscslp.2016.7918381","mag":"2963300763"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5050701255","display_name":"Lantian Li","orcid":"https://orcid.org/0000-0003-4274-7930"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lantian Li","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107981608","display_name":"Chao Xing","orcid":"https://orcid.org/0000-0003-1120-8803"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Xing","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077201253","display_name":"Kaimin Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaimin Yu","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084318285","display_name":"Thomas Fang Zheng","orcid":"https://orcid.org/0000-0002-0249-4767"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Thomas Fang Zheng","raw_affiliation_strings":["Center for Speech and Language Technologies, Tsinghua University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Speech and Language Technologies, Tsinghua University, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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":0.9965999722480774,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.995199978351593,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6869513392448425},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5545821189880371},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.49265843629837036},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.436758816242218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2952287197113037},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.155470609664917},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.1234796941280365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869513392448425},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5545821189880371},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49265843629837036},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.436758816242218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2952287197113037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.155470609664917},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.1234796941280365}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918381","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W1589137271","https://openalex.org/W1916834241","https://openalex.org/W1985123706","https://openalex.org/W2107638917","https://openalex.org/W2112582577","https://openalex.org/W2113307832","https://openalex.org/W2145065594","https://openalex.org/W2147442641","https://openalex.org/W2147717514","https://openalex.org/W2150769028","https://openalex.org/W2160371485","https://openalex.org/W2404719667","https://openalex.org/W4230940751","https://openalex.org/W6629956336","https://openalex.org/W6640010188","https://openalex.org/W6681846431"],"related_works":["https://openalex.org/W2893763841","https://openalex.org/W2368779261","https://openalex.org/W2794438528","https://openalex.org/W2794527914","https://openalex.org/W2778699561","https://openalex.org/W1503053695","https://openalex.org/W3204597924","https://openalex.org/W2995996972","https://openalex.org/W2312116756","https://openalex.org/W1765329493"],"abstract_inverted_index":{"The":[0],"popular":[1],"i-vector":[2],"model":[3],"represents":[4],"speakers":[5],"as":[6],"low-dimensional":[7],"continuous":[8,18],"vectors":[9,34],"(i-vectors),":[10],"and":[11,129,136],"hence":[12],"it":[13],"is":[14,68,91],"a":[15,37,47,57,94],"way":[16],"of":[17,59,66,102],"speaker":[19,27,116,127],"embedding.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"investigate":[25],"binary":[26,33,52,108,115],"embedding,":[28],"which":[29],"transforms":[30],"i-vectors":[31,105],"to":[32,106],"(codes)":[35],"by":[36,93],"hash":[38,61,73,89],"function.":[39],"We":[40,78],"start":[41],"from":[42,56],"locality":[43],"sensitive":[44],"hashing":[45],"(LSH),":[46],"simple":[48],"binarization":[49],"approach":[50],"where":[51,87],"codes":[53,109],"are":[54,140],"derived":[55],"set":[58],"random":[60],"functions.":[62],"A":[63],"potential":[64],"problem":[65],"LSH":[67],"that":[69,98,114],"the":[70,88,103,133,137],"randomly":[71],"sampled":[72],"functions":[74],"might":[75],"be":[76],"suboptimal.":[77],"therefore":[79],"propose":[80],"an":[81],"improved":[82],"Hamming":[83],"distance":[84],"learning":[85],"approach,":[86],"function":[90],"learned":[92],"variable-sized":[95,107],"block":[96],"training":[97],"projects":[99],"each":[100],"dimension":[101],"original":[104],"independently.":[110],"Our":[111],"experiments":[112],"show":[113],"embedding":[117],"can":[118],"deliver":[119],"competitive":[120],"or":[121],"even":[122],"better":[123],"results":[124],"on":[125],"both":[126],"verification":[128],"identification":[130],"tasks,":[131],"while":[132],"memory":[134],"usage":[135],"computation":[138],"cost":[139],"significantly":[141],"reduced.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}