{"id":"https://openalex.org/W1536623512","doi":"https://doi.org/10.1007/pl00021522","title":"Multimedia document retrieval using speech and speaker recognition","display_name":"Multimedia document retrieval using speech and speaker recognition","publication_year":2000,"publication_date":"2000-06-01","ids":{"openalex":"https://openalex.org/W1536623512","doi":"https://doi.org/10.1007/pl00021522","mag":"1536623512"},"language":"en","primary_location":{"id":"doi:10.1007/pl00021522","is_oa":false,"landing_page_url":"https://doi.org/10.1007/pl00021522","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition","raw_type":"journal-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/A5076852218","display_name":"Mahesh Viswanathan","orcid":"https://orcid.org/0000-0001-7977-0080"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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":"Mahesh Viswanathan","raw_affiliation_strings":["IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com\n, , , , , , US","IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com#N#, , US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com\n, , , , , , US","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com#N#, , US","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030917082","display_name":"Homayoon Beigi","orcid":"https://orcid.org/0000-0003-0127-2385"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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":"Homayoon S.M. Beigi","raw_affiliation_strings":["IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com\n, , , , , , US","IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com#N#, , US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com\n, , , , , , US","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com#N#, , US","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054081510","display_name":"S. Dharanipragada","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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":"Satya Dharanipragada","raw_affiliation_strings":["IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com\n, , , , , , US","IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com#N#, , US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com\n, , , , , , US","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com#N#, , US","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071280490","display_name":"Fereydoun Maali","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]},{"id":"https://openalex.org/I4210151799","display_name":"Siemens Healthcare (United States)","ror":"https://ror.org/054962n91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210151799"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fereydoun Maali","raw_affiliation_strings":["Signal Recognition Corporation, P.O. Box 7010, New York, NY 10128, USA; e-mail: maali-sigrec@worldnet.att.net\n, , , , , , US","Signal Recognition Corporation, P.O. Box 7010, New York, NY 10128, USA; e-mail: maali-sigrec@worldnet.att.net , US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Signal Recognition Corporation, P.O. Box 7010, New York, NY 10128, USA; e-mail: maali-sigrec@worldnet.att.net\n, , , , , , US","institution_ids":["https://openalex.org/I4210151799"]},{"raw_affiliation_string":"Signal Recognition Corporation, P.O. Box 7010, New York, NY 10128, USA; e-mail: maali-sigrec@worldnet.att.net , US","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001809723","display_name":"Alain Tritschler","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"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":"Alain Tritschler","raw_affiliation_strings":["IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com\n, , , , , , US","IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com#N#, , US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com\n, , , , , , US","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM T.J. Watson Research Center, P.O. Box 218, Yorktown Heights, NY 10598, USA; e-mail: {maheshv, beigi, dsatya}@watson.ibm.com, trischl@ifrance.com#N#, , US","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.06863623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":"4","first_page":"147","last_page":"162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9977999925613403,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9958000183105469,"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":0.870339035987854},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6693891286849976},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6049150228500366},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6035779714584351},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5323424935340881},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4933396875858307},{"id":"https://openalex.org/keywords/speech-analytics","display_name":"Speech analytics","score":0.43269628286361694},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4314623177051544},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.42226383090019226},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4048125743865967},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3698945939540863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34248971939086914},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3414725065231323},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.3165212869644165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.870339035987854},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6693891286849976},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6049150228500366},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6035779714584351},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5323424935340881},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4933396875858307},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.43269628286361694},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4314623177051544},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.42226383090019226},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4048125743865967},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3698945939540863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34248971939086914},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3414725065231323},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3165212869644165},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/pl00021522","is_oa":false,"landing_page_url":"https://doi.org/10.1007/pl00021522","pdf_url":null,"source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W21371201","https://openalex.org/W32283220","https://openalex.org/W125260059","https://openalex.org/W1482605500","https://openalex.org/W1538424569","https://openalex.org/W1560013842","https://openalex.org/W1566367736","https://openalex.org/W1570542661","https://openalex.org/W1590118338","https://openalex.org/W1969228515","https://openalex.org/W2008957275","https://openalex.org/W2073896599","https://openalex.org/W2074188409","https://openalex.org/W2103892053","https://openalex.org/W2106420626","https://openalex.org/W2128011037","https://openalex.org/W2142635246","https://openalex.org/W2149630107","https://openalex.org/W2151299225","https://openalex.org/W2907162034"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1493012537","https://openalex.org/W2157598242","https://openalex.org/W2619911963","https://openalex.org/W2964829415","https://openalex.org/W2903652364","https://openalex.org/W2567369127","https://openalex.org/W3089379469","https://openalex.org/W4321847012","https://openalex.org/W3151376046"],"abstract_inverted_index":null,"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}
