{"id":"https://openalex.org/W2024700055","doi":"https://doi.org/10.1007/bf02277195","title":"Speaker indexing using neural network clustering of vowel spectra","display_name":"Speaker indexing using neural network clustering of vowel spectra","publication_year":1997,"publication_date":"1997-03-01","ids":{"openalex":"https://openalex.org/W2024700055","doi":"https://doi.org/10.1007/bf02277195","mag":"2024700055"},"language":"en","primary_location":{"id":"doi:10.1007/bf02277195","is_oa":false,"landing_page_url":"https://doi.org/10.1007/bf02277195","pdf_url":null,"source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"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 of Speech Technology","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/A5004281470","display_name":"Deb Roy","orcid":"https://orcid.org/0000-0002-2780-4768"},"institutions":[{"id":"https://openalex.org/I4210142372","display_name":"Human Media","ror":"https://ror.org/04072nk43","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210142372"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Deb K. Roy","raw_affiliation_strings":["MIT Media Lab, 20 Ames St., 02139, Cambridge, MA","MIT Media Lab, Cambridge#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT Media Lab, 20 Ames St., 02139, Cambridge, MA","institution_ids":["https://openalex.org/I4210142372"]},{"raw_affiliation_string":"MIT Media Lab, Cambridge#TAB#","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004281470"],"corresponding_institution_ids":["https://openalex.org/I4210142372","https://openalex.org/I63966007"],"apc_list":{"value":2780,"currency":"USD","value_usd":2780},"apc_paid":null,"fwci":0.3931,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.64420063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":"2","first_page":"143","last_page":"149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9918000102043152,"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":0.9918000102043152,"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/T10320","display_name":"Neural Networks and Applications","score":0.9916999936103821,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9896000027656555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8895382881164551},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.882086992263794},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6860272884368896},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.658816933631897},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.5720971822738647},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.4869140386581421},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4802265763282776},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.43251559138298035},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4105128049850464},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3590250015258789}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8895382881164551},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.882086992263794},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6860272884368896},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.658816933631897},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5720971822738647},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.4869140386581421},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4802265763282776},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.43251559138298035},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4105128049850464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3590250015258789}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/bf02277195","is_oa":false,"landing_page_url":"https://doi.org/10.1007/bf02277195","pdf_url":null,"source":{"id":"https://openalex.org/S4650632","display_name":"International Journal of Speech Technology","issn_l":"1381-2416","issn":["1381-2416","1572-8110"],"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 of Speech Technology","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.49.1080","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.49.1080","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://dkroy.www.media.mit.edu/people/dkroy/papers/Postscript/ijst96.ps.Z","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.134","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://web.media.mit.edu/~dkroy/papers/pdf/roy_1997.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W43375627","https://openalex.org/W120083323","https://openalex.org/W1498436455","https://openalex.org/W1551816323","https://openalex.org/W2028186856","https://openalex.org/W2151299225","https://openalex.org/W2152816769","https://openalex.org/W2188206772","https://openalex.org/W6632924608"],"related_works":["https://openalex.org/W1492025301","https://openalex.org/W2171511892","https://openalex.org/W2101169486","https://openalex.org/W2915312149","https://openalex.org/W119794901","https://openalex.org/W2991474544","https://openalex.org/W2091220214","https://openalex.org/W1830436187","https://openalex.org/W2339627829","https://openalex.org/W2155316557"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}