{"id":"https://openalex.org/W2133564850","doi":"https://doi.org/10.1109/icassp.2011.5947562","title":"Recent development of discriminative training using non-uniform criteria for cross-level acoustic modeling","display_name":"Recent development of discriminative training using non-uniform criteria for cross-level acoustic modeling","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2133564850","doi":"https://doi.org/10.1109/icassp.2011.5947562","mag":"2133564850"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Weng","raw_affiliation_strings":["Center of Signal and Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","Center for Signal and Image Processing, Georgia Institute of Technology, 75 Fifth Street NW Atlanta, 30308, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Signal and Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Institute of Technology, 75 Fifth Street NW Atlanta, 30308, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070867959","display_name":"Biing\u2010Hwang Juang","orcid":"https://orcid.org/0000-0002-5773-5679"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Biing-Hwang Juang","raw_affiliation_strings":["Center of Signal and Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","Center for Signal and Image Processing, Georgia Institute of Technology, 75 Fifth Street NW Atlanta, 30308, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Signal and Image Processing, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Center for Signal and Image Processing, Georgia Institute of Technology, 75 Fifth Street NW Atlanta, 30308, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.5396,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64502401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5332","last_page":"5335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.9991000294685364,"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":0.8484082221984863},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7827881574630737},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7393569946289062},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7095661759376526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.623686671257019},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.615605890750885},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.5866956114768982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4282025694847107},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3581533432006836},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18711790442466736}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8484082221984863},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7827881574630737},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7393569946289062},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7095661759376526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.623686671257019},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.615605890750885},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.5866956114768982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4282025694847107},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3581533432006836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18711790442466736},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947562","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947562","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W151602794","https://openalex.org/W1877570817","https://openalex.org/W1979136262","https://openalex.org/W2063541597","https://openalex.org/W2070737455","https://openalex.org/W2106359072","https://openalex.org/W2134659216","https://openalex.org/W2170930194"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W1997182898","https://openalex.org/W2061937230","https://openalex.org/W2162582511","https://openalex.org/W2189081180","https://openalex.org/W2944691285"],"abstract_inverted_index":{"In":[0,115],"this":[1],"paper,":[2],"we":[3],"extend":[4],"our":[5],"previous":[6],"study":[7],"on":[8,22,73,150],"discriminative":[9,169],"training":[10,170],"using":[11,77],"non-uniform":[12,54],"criteria":[13],"for":[14,92],"speech":[15],"recognition.":[16],"The":[17],"work":[18],"will":[19],"put":[20],"emphasis":[21],"how":[23],"the":[24,29,40,53,61,66,74,78,82,86,89,103,108,112,119,123,129,134,141,157,160,179],"acoustic":[25,124],"modeling":[26],"interacts":[27],"with":[28],"risk":[30,67],"at":[31,60,111],"a":[32,146,151],"higher":[33],"level,":[34],"which":[35,163],"is":[36,57,138],"more":[37],"relevant":[38],"to":[39,64,117],"most":[41],"used":[42],"evaluation":[43,130],"measures,":[44],"e.g.,":[45],"word":[46,62,75,95,105,109],"error":[47,55,136],"rate":[48],"(WER).":[49],"To":[50],"be":[51],"specific,":[52],"cost":[56,137],"first":[58],"derived":[59,135],"level":[63,120],"minimize":[65],"w.r.t.":[68],"WER":[69],"and":[70,107,128,172],"then":[71],"computed":[72],"lattice":[76,110],"forward-backward":[79,87],"algorithm.":[80],"With":[81],"statistics":[83],"obtained":[84],"from":[85],"algorithm,":[88],"competing":[90],"hypotheses":[91],"each":[93],"label":[94,104],"are":[96],"searched":[97],"by":[98],"performing":[99],"dynamic":[100],"programming":[101],"between":[102,122],"sequence":[106],"phone":[113],"level.":[114],"order":[116],"alleviate":[118],"inconsistency":[121],"model":[125],"(phone":[126],"level)":[127],"measure":[131],"(word":[132],"level),":[133],"embedded":[139],"into":[140],"overall":[142,161],"objective":[143],"function":[144],"in":[145],"cross-level":[147],"fashion.":[148],"Experiments":[149],"large":[152],"vocabulary":[153],"task":[154],"WSJO":[155],"demonstrate":[156],"effectiveness":[158],"of":[159],"approach,":[162],"show":[164],"it":[165],"outperforms":[166],"two":[167],"prevalent":[168],"methods":[171],"achieves":[173],"about":[174],"13%":[175],"relative":[176],"improvement":[177],"over":[178],"baseline":[180],"system.":[181]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}