{"id":"https://openalex.org/W2125743092","doi":"https://doi.org/10.1109/icassp.2012.6288981","title":"Discriminative feature transforms using differenced maximum mutual information","display_name":"Discriminative feature transforms using differenced maximum mutual information","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2125743092","doi":"https://doi.org/10.1109/icassp.2012.6288981","mag":"2125743092"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5023868166","display_name":"Marc Delcroix","orcid":"https://orcid.org/0000-0002-5175-7834"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Marc Delcroix","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101949937","display_name":"Atsunori Ogawa","orcid":"https://orcid.org/0000-0002-2888-101X"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsunori Ogawa","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]},{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["JP","US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Inc., USA","NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Inc., USA","institution_ids":["https://openalex.org/I4210159266"]},{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021240106","display_name":"Tomohiro Nakatani","orcid":"https://orcid.org/0000-0002-7487-7150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomohiro Nakatani","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018620798","display_name":"Atsushi Nakamura","orcid":"https://orcid.org/0000-0003-0788-2221"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Atsushi Nakamura","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4753","last_page":"4756"},"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9994000196456909,"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/discriminative-model","display_name":"Discriminative model","score":0.9345109462738037},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.7474858164787292},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.702802836894989},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.6260614395141602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6205681562423706},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5779604315757751},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5758426189422607},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5732888579368591},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.5517501831054688},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5422642230987549},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46296265721321106},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.4297380745410919},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3645226061344147}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9345109462738037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.7474858164787292},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.702802836894989},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.6260614395141602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6205681562423706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5779604315757751},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5758426189422607},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5732888579368591},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.5517501831054688},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5422642230987549},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46296265721321106},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.4297380745410919},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3645226061344147},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W34922426","https://openalex.org/W1984196678","https://openalex.org/W2005076803","https://openalex.org/W2097427452","https://openalex.org/W2102804087","https://openalex.org/W2125234026","https://openalex.org/W2125610823","https://openalex.org/W2129057864","https://openalex.org/W2134218976","https://openalex.org/W2138889249","https://openalex.org/W2143908786","https://openalex.org/W2148577181","https://openalex.org/W2150907703","https://openalex.org/W2158808283","https://openalex.org/W2164115090","https://openalex.org/W2396455701","https://openalex.org/W6651845459","https://openalex.org/W6682398751"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W2146591867","https://openalex.org/W2075383893","https://openalex.org/W156213964","https://openalex.org/W2050960118","https://openalex.org/W1992295166","https://openalex.org/W2143508933"],"abstract_inverted_index":{"Recently":[0],"feature":[1,6,24,36,84,131],"compensation":[2,47],"techniques":[3],"that":[4,103,141,148],"train":[5],"transforms":[7,132],"using":[8,54],"a":[9,29,35,136],"discriminative":[10,76,130],"criterion":[11,102,128],"have":[12,78],"attracted":[13],"much":[14],"interest":[15],"in":[16,135],"the":[17,22,44,55,64,69,83,98,123,126],"speech":[18,138],"recognition":[19,139,144],"community.":[20],"Typically,":[21],"acoustic":[23,115],"space":[25],"is":[26,38,48],"modeled":[27],"by":[28,51,68],"Gaussian":[30,42],"mixture":[31],"model":[32,116],"(GMM),":[33],"and":[34,92,133],"transform":[37],"assigned":[39],"to":[40,110,147],"each":[41,59,73],"of":[43,72,125,149],"GMM.":[45],"Feature":[46],"then":[49,61],"performed":[50],"transforming":[52],"features":[53,66],"transformation":[56,85],"associated":[57],"with":[58],"Gaussian,":[60],"summing":[62],"up":[63],"transformed":[65],"weighted":[67],"posterior":[70],"probability":[71],"Gaussian.":[74],"Several":[75],"criteria":[77],"been":[79,108],"investigated":[80],"for":[81,114,129],"estimating":[82],"parameters":[86],"including":[87],"maximum":[88],"mutual":[89],"information":[90],"(MMI)":[91],"minimum":[93],"phone":[94],"error":[95],"(MPE).":[96],"Recently,":[97],"differenced":[99],"MMI":[100,105,150],"(dMMI)":[101],"generalizes":[104],"andMPE,":[106],"has":[107],"shown":[109],"provide":[111],"competitive":[112],"performance":[113,145],"training.":[117],"In":[118],"this":[119],"paper,":[120],"we":[121],"investigate":[122],"use":[124],"dMMI":[127,142],"demonstrate":[134],"noisy":[137],"experiment":[140],"achieves":[143],"superior":[146],"or":[151],"MPE.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}