{"id":"https://openalex.org/W2025487094","doi":"https://doi.org/10.1109/icassp.2013.6639088","title":"Subspace mixture model for low-resource speech recognition in cross-lingual settings","display_name":"Subspace mixture model for low-resource speech recognition in cross-lingual settings","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2025487094","doi":"https://doi.org/10.1109/icassp.2013.6639088","mag":"2025487094"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2013.6639088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5003251887","display_name":"Yajie Miao","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yajie Miao","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, United States","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110453805","display_name":"Alex Waibel","orcid":null},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alex Waibel","raw_affiliation_strings":["Karlsruhe Institute of Technology, Karlsruhe, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology, Karlsruhe, Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6017,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.84576852,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"7339","last_page":"7343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9988999962806702,"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":0.9876999855041504,"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/subspace-topology","display_name":"Subspace topology","score":0.9235138297080994},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8039250373840332},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.6953384280204773},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6464076638221741},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5625383853912354},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.4713396728038788},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4656335413455963},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44250452518463135},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4410468339920044},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4405035972595215},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4330509901046753},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.41983890533447266},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40219834446907043},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14005020260810852},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09050232172012329}],"concepts":[{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.9235138297080994},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8039250373840332},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.6953384280204773},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6464076638221741},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5625383853912354},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.4713396728038788},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4656335413455963},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44250452518463135},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4410468339920044},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4405035972595215},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4330509901046753},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.41983890533447266},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40219834446907043},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14005020260810852},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09050232172012329},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2013.6639088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2013.6639088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.710.770","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.710.770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/%7Eymiao/pub/smm_final_icassp13.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306078","display_name":"U.S. Department of Defense","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W66627554","https://openalex.org/W1981706894","https://openalex.org/W1991180839","https://openalex.org/W2002342963","https://openalex.org/W2123798005","https://openalex.org/W2125007694","https://openalex.org/W2138632432","https://openalex.org/W2151402979","https://openalex.org/W6602682705"],"related_works":["https://openalex.org/W2896134808","https://openalex.org/W3172436493","https://openalex.org/W4287164812","https://openalex.org/W2957492749","https://openalex.org/W1887135636","https://openalex.org/W2386063599","https://openalex.org/W1975884855","https://openalex.org/W3213150849","https://openalex.org/W4285605394","https://openalex.org/W2025894073"],"abstract_inverted_index":{"The":[0,13],"subspace":[1,19,47,53,86],"Gaussian":[2],"mixture":[3,48,64],"model":[4,49,79],"(SGMM)":[5],"has":[6,106],"been":[7],"exploited":[8],"for":[9],"cross-lingual":[10],"speech":[11],"recognition.":[12],"general":[14],"motivation":[15],"is":[16],"that":[17,94],"the":[18,32,56,66,75,83,89,95,103],"parameters":[20,54],"can":[21],"be":[22],"estimated":[23],"on":[24,55,88],"multiple":[25],"source":[26,70],"languages":[27],"and":[28],"then":[29],"transferred":[30],"to":[31,42,45],"target":[33,57,90,104],"language.":[34,91],"In":[35],"this":[36],"work,":[37],"we":[38],"investigate":[39],"an":[40],"extension":[41],"SGMM,":[43],"referred":[44],"as":[46,61],"(SMM),":[50],"in":[51],"which":[52],"language":[58,105],"are":[59],"casted":[60],"a":[62],"linear":[63],"of":[65,77,85],"subspaces":[67],"derived":[68],"from":[69],"languages.":[71],"This":[72],"approach":[73],"reduces":[74],"number":[76],"SGMM":[78,100],"parameters,":[80],"while":[81],"retaining":[82],"flexibility":[84],"learning":[87],"Experiments":[92],"show":[93],"proposed":[96],"SMM":[97],"method":[98],"outperforms":[99],"significantly":[101],"when":[102],"limited":[107],"training":[108],"data.":[109]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}