{"id":"https://openalex.org/W2719865699","doi":"https://doi.org/10.1109/icassp.2017.7953257","title":"Topic identification of spoken documents using unsupervised acoustic unit discovery","display_name":"Topic identification of spoken documents using unsupervised acoustic unit discovery","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2719865699","doi":"https://doi.org/10.1109/icassp.2017.7953257","mag":"2719865699"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7953257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5008468618","display_name":"Santosh Kesiraju","orcid":"https://orcid.org/0000-0002-3725-742X"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Santosh Kesiraju","raw_affiliation_strings":["Brno University of Technology, Speech@Fit and IT4I Center of Excellence, Brno, Czech Republic","Faculty of Information Technology [Brno]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@Fit and IT4I Center of Excellence, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology [Brno]","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040448607","display_name":"Raghavendra Pappagari","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ","US"],"is_corresponding":false,"raw_author_name":"Raghavendra Pappagari","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, U. S. A","Faculty of Information Technology [Brno]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, U. S. A","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Faculty of Information Technology [Brno]","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104831405","display_name":"Lucas Ondel","orcid":"https://orcid.org/0000-0003-4512-0471"},"institutions":[{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]},{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ","GR"],"is_corresponding":false,"raw_author_name":"Lucas Ondel","raw_affiliation_strings":["Brno University of Technology, Speech@Fit and IT4I Center of Excellence, Brno, Czech Republic","Center for Language and Speech Processing [Baltimore]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@Fit and IT4I Center of Excellence, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Center for Language and Speech Processing [Baltimore]","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Lukas Burget","raw_affiliation_strings":["Brno University of Technology, Speech@Fit and IT4I Center of Excellence, Brno, Czech Republic","Faculty of Information Technology [Brno]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology, Speech@Fit and IT4I Center of Excellence, Brno, Czech Republic","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Faculty of Information Technology [Brno]","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, U. S. A","Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, U. S. A","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, U. S. A","Center for Language and Speech Processing [Baltimore]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, U. S. A","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Center for Language and Speech Processing [Baltimore]","institution_ids":["https://openalex.org/I4210098364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Cernocky","raw_affiliation_strings":["Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00c3\u00bd, CZ","Brno University of Technology  [Brno]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vysoke uceni technicke v Brne, Brno, Moravskoslezsk\u00c3\u00bd, CZ","institution_ids":["https://openalex.org/I60587646"]},{"raw_affiliation_string":"Brno University of Technology  [Brno]","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113813881","display_name":"Suryakanth Gansgashetty","orcid":null},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Suryakanth V Gangashetty","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad, India","International Institute of Information Technology, Hyderabad [Hyderabad]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad, India","institution_ids":["https://openalex.org/I64189192"]},{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad [Hyderabad]","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6808,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.85321414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"5745","last_page":"5749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9988999962806702,"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":0.9950000047683716,"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/computer-science","display_name":"Computer science","score":0.8089057803153992},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6996209025382996},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6689456701278687},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6172524094581604},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5888357758522034},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5405105948448181},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4528159201145172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4382096827030182},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.43389129638671875},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.41198045015335083},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39519938826560974},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06214016675949097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8089057803153992},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6996209025382996},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6689456701278687},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6172524094581604},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5888357758522034},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5405105948448181},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4528159201145172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4382096827030182},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.43389129638671875},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.41198045015335083},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39519938826560974},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06214016675949097},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7953257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7953257","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310145","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W51277926","https://openalex.org/W66627554","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W1967687583","https://openalex.org/W2009388533","https://openalex.org/W2025205509","https://openalex.org/W2062914951","https://openalex.org/W2078769636","https://openalex.org/W2100768664","https://openalex.org/W2101234009","https://openalex.org/W2112107221","https://openalex.org/W2113651538","https://openalex.org/W2127498532","https://openalex.org/W2130180273","https://openalex.org/W2131342762","https://openalex.org/W2142749559","https://openalex.org/W2168363555","https://openalex.org/W2347098582","https://openalex.org/W2398569491","https://openalex.org/W2564058731","https://openalex.org/W6602092770","https://openalex.org/W6602682705","https://openalex.org/W6631362777","https://openalex.org/W6675022971","https://openalex.org/W6677106874"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2153098279"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,49,59,66],"application":[4],"of":[5,15],"unsupervised":[6],"acoustic":[7,20,60],"unit":[8,21,61],"discovery":[9,22],"for":[10,58],"topic":[11,51],"identification":[12],"(topic":[13],"ID)":[14],"spoken":[16],"audio":[17],"documents.":[18],"The":[19,40],"method":[23,68],"is":[24],"based":[25,74],"on":[26,75],"a":[27,34],"non-parametric":[28],"Bayesian":[29],"phone-loop":[30],"model":[31],"that":[32,65,72],"segments":[33],"speech":[35],"utterance":[36],"into":[37,48],"phone-like":[38,42],"categories.":[39],"discovered":[41],"(acoustic)":[43],"units":[44],"are":[45,73],"further":[46],"fed":[47],"conventional":[50],"ID":[52],"framework.":[53],"Using":[54],"multilingual":[55],"bottleneck":[56],"features":[57],"discovery,":[62],"we":[63],"show":[64],"proposed":[67],"outperforms":[69],"other":[70],"systems":[71],"cross-lingual":[76],"phoneme":[77],"recognizer.":[78]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}