{"id":"https://openalex.org/W2164889029","doi":"https://doi.org/10.1109/icme.2005.1521586","title":"CSR: Speaker Recognition from Compressed VoIP Packet Stream","display_name":"CSR: Speaker Recognition from Compressed VoIP Packet Stream","publication_year":2005,"publication_date":"2005-10-24","ids":{"openalex":"https://openalex.org/W2164889029","doi":"https://doi.org/10.1109/icme.2005.1521586","mag":"2164889029"},"language":"en","primary_location":{"id":"doi:10.1109/icme.2005.1521586","doi":"https://doi.org/10.1109/icme.2005.1521586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521586","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5028089542","display_name":"Char\u0173 C. Aggarwal","orcid":"https://orcid.org/0000-0003-2579-7581","observed_orcids":["https://orcid.org/0000-0003-2579-7581"]},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Aggarwal","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033879427","display_name":"David P. Olshefski","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Olshefski","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":null,"display_name":"D. Saha","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Saha","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082169032","display_name":"Zon\u2010Yin Shae","orcid":"https://orcid.org/0000-0003-1709-5416","observed_orcids":["https://orcid.org/0000-0003-1709-5416"]},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zon-Yin Shae","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968","observed_orcids":["https://orcid.org/0000-0002-3491-5968"]},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Yu","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":1.7513,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.86137566,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"970","last_page":"973"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9878000020980835,"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":0.9878000020980835,"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":0.009600000455975533,"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":0.0006000000284984708,"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/speaker-recognition","display_name":"speaker recognition","score":0.6890000104904175},{"id":"https://openalex.org/keywords/voip","display_name":"VoIP","score":0.925000011920929},{"id":"https://openalex.org/keywords/fast-clustering","display_name":"fast clustering","score":0.6340000033378601},{"id":"https://openalex.org/keywords/feature-subsets","display_name":"feature subsets","score":0.44999998807907104},{"id":"https://openalex.org/keywords/real-time-speech-processing","display_name":"real-time speech processing","score":0.5550000071525574}],"concepts":[{"id":"https://openalex.org/C171246234","wikidata":"https://www.wikidata.org/wiki/Q81945","display_name":"Voice over IP","level":3,"score":0.7519901394844055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487158179283142},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.6904153823852539},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5979839563369751},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5249595642089844},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.42973411083221436},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.42723333835601807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26675164699554443},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.21175330877304077},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.12346717715263367},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08214071393013},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icme.2005.1521586","doi":"https://doi.org/10.1109/icme.2005.1521586","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme.2005.1521586","pdf_url":null,"source":{"id":"https://openalex.org/S4363607799","display_name":"IEEE International Conference on Multimedia and Expo (ICME)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2005 IEEE International Conference on Multimedia and Expo","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.911.6702","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.911.6702","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cecs.uci.edu/%7Epapers/icme05/defevent/papers/cr1552.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W43959665","https://openalex.org/W1949687736","https://openalex.org/W1971784203","https://openalex.org/W2165880886","https://openalex.org/W2170936641","https://openalex.org/W2506214260"],"related_works":["https://openalex.org/W2362292274","https://openalex.org/W2146618249","https://openalex.org/W2109906699","https://openalex.org/W2129295797","https://openalex.org/W2377454556","https://openalex.org/W2380449690","https://openalex.org/W1927009935","https://openalex.org/W1777198990","https://openalex.org/W1988273885","https://openalex.org/W2109516288"],"abstract_inverted_index":{"VoIP":[0],"applications":[1],"require":[2],"the":[3,27,53],"ability":[4],"to":[5,21],"identify":[6],"speakers":[7,77],"in":[8,56],"real":[9],"time.":[10],"This":[11],"paper":[12],"presents":[13],"compressed":[14,28,41,58],"speaker":[15,23,34],"recognition":[16,24,35],"(CSR),":[17],"an":[18],"innovative":[19],"approach":[20],"perform":[22],"directly":[25],"from":[26,36],"voice":[29,42,59],"packets.":[30],"CSR":[31,66],"performs":[32],"online":[33],"live":[37],"packet":[38],"streams":[39],"of":[40,52,76],"packets":[43],"by":[44],"performing":[45],"fast":[46],"clustering":[47],"over":[48],"a":[49,73],"defined":[50],"subset":[51],"features":[54],"available":[55],"each":[57],"packet.":[60],"Our":[61],"experimental":[62],"results":[63],"show":[64],"that":[65],"is":[67],"highly":[68],"scalable":[69],"and":[70],"accurate":[71],"across":[72],"broad":[74],"range":[75]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2016-06-24T00:00:00"}
