{"id":"https://openalex.org/W2407540397","doi":"https://doi.org/10.21437/interspeech.2012-173","title":"Discriminative reranking for LVCSR leveraging invariant structure","display_name":"Discriminative reranking for LVCSR leveraging invariant structure","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2407540397","doi":"https://doi.org/10.21437/interspeech.2012-173","mag":"2407540397"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-173","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5028421346","display_name":"Masayuki Suzuki","orcid":"https://orcid.org/0000-0002-0436-1490"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masayuki Suzuki","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021294422","display_name":"Gakuto Kurata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gakuto Kurata","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083574298","display_name":"Masafumi Nishimura","orcid":"https://orcid.org/0000-0001-7633-9340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masafumi Nishimura","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5041213266","display_name":"Nobuaki Minematsu","orcid":"https://orcid.org/0000-0002-8778-9555"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nobuaki Minematsu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"563","last_page":"566"},"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/T11309","display_name":"Music 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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973999857902527,"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/discriminative-model","display_name":"Discriminative model","score":0.8942795395851135},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8072844743728638},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6982485055923462},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6806261539459229},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.652463972568512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5800607204437256},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5696043968200684},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5637609958648682},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4686543047428131},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4544534981250763},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42709240317344666},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11520114541053772},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07217782735824585}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8942795395851135},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072844743728638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6982485055923462},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6806261539459229},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.652463972568512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5800607204437256},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5696043968200684},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5637609958648682},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4686543047428131},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4544534981250763},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42709240317344666},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11520114541053772},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07217782735824585},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-173","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-173","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.587.2102","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.587.2102","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.gavo.t.u-tokyo.ac.jp/~mine/paper/PDF/2012/INTERSPEECH_876_t2012-9.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W179314280","https://openalex.org/W1557806084","https://openalex.org/W2098318492","https://openalex.org/W2121127625","https://openalex.org/W2136727248","https://openalex.org/W2151660570","https://openalex.org/W2156172072","https://openalex.org/W2158025800","https://openalex.org/W2158195707","https://openalex.org/W2164805947","https://openalex.org/W2168199160","https://openalex.org/W2185719453","https://openalex.org/W2400749559","https://openalex.org/W2886269827","https://openalex.org/W3021452258"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2053269318","https://openalex.org/W2110523656","https://openalex.org/W2153098279"],"abstract_inverted_index":{"An":[0],"invariant":[1,33,68,79,102],"structure":[2,69],"is":[3,81],"one":[4],"of":[5,37,59,83,97,113,133],"the":[6,32,78,90,101,106,114,118,137],"long-span":[7],"acoustic":[8,11],"represen-tations,":[9],"where":[10,117],"variations":[12],"caused":[13],"by":[14,123],"non-linguistic":[15],"fac-tors":[16],"are":[17,120],"effectively":[18],"removed":[19],"from":[20],"speech.":[21],"We":[22],"present":[23],"in":[24,89,100],"this":[25],"pa-per":[26],"a":[27,50,57,95,110,129],"new":[28],"method":[29],"to":[30,55],"leverage":[31],"structures":[34],"as":[35],"features":[36],"discriminative":[38],"reranking":[39,148],"for":[40,70],"Large":[41],"Vocabulary":[42],"Continuous":[43],"Speech":[44],"Recognition":[45],"(LVCSR).":[46],"First":[47],"we":[48,93],"use":[49],"traditional":[51],"HMM-based":[52,139],"LVCSR":[53,140],"system":[54],"get":[56],"list":[58],"N-best":[60,107],"candidates":[61,108],"with":[62],"phone":[63,75],"alignments":[64],"and":[65,104],"construct":[66],"an":[67],"each":[71,98],"candidate":[72],"using":[73,109],"its":[74],"alignment.":[76],"Here,":[77],"struc-ture":[80],"composed":[82],"lengths":[84],"between":[85],"every":[86],"two":[87],"phonemes":[88],"candidate.":[91],"Then":[92],"estimate":[94],"score":[96],"phoneme-pair":[99,115],"structure,":[103],"rerank":[105],"weighted":[111],"sum":[112],"scores,":[116],"weights":[119],"trained":[121],"discriminatively":[122],"averaged":[124],"perceptron.":[125],"Experi-mental":[126],"results":[127],"show":[128],"relative":[130],"CER":[131],"improvement":[132],"6.69":[134],"%":[135],"over":[136],"baseline":[138],"system.":[141],"Index":[142],"Terms:":[143],"Invariant":[144],"Structure,":[145],"LVCSR,":[146],"Discriminative":[147],"1.":[149]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}