{"id":"https://openalex.org/W2146666569","doi":"https://doi.org/10.1109/icassp.2005.1415063","title":"Minimum Classification Error for Large Scale Speech Recognition Tasks using Weighted Finite State Transducers","display_name":"Minimum Classification Error for Large Scale Speech Recognition Tasks using Weighted Finite State Transducers","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2146666569","doi":"https://doi.org/10.1109/icassp.2005.1415063","mag":"2146666569"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},"type":"article","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/A5030109648","display_name":"Erik McDermott","orcid":null},"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":true,"raw_author_name":"E. McDermott","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027443847","display_name":"Shigeru Katagiri","orcid":"https://orcid.org/0000-0003-4738-5385"},"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":"S. Katagiri","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030109648"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":3.1622,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.92118956,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"113","last_page":"116"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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":0.9976000189781189,"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":0.8785709738731384},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7767958045005798},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7508003115653992},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7297921776771545},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6185199022293091},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5824532508850098},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5659815073013306},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5237736105918884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5205867886543274},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43818336725234985},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43488267064094543},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4288231134414673},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4102356433868408},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39247509837150574},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2937779426574707},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11157289147377014},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07177993655204773}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8785709738731384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767958045005798},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7508003115653992},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7297921776771545},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6185199022293091},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5824532508850098},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5659815073013306},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5237736105918884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5205867886543274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43818336725234985},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43488267064094543},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4288231134414673},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4102356433868408},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39247509837150574},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2937779426574707},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11157289147377014},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07177993655204773},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.699999988079071,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W87954838","https://openalex.org/W1508752711","https://openalex.org/W1533051419","https://openalex.org/W1956550074","https://openalex.org/W1979136262","https://openalex.org/W2046932483","https://openalex.org/W2085684370","https://openalex.org/W2140914930","https://openalex.org/W2150907703","https://openalex.org/W2162432783","https://openalex.org/W2276256113","https://openalex.org/W2336725036","https://openalex.org/W2395140404","https://openalex.org/W6603550504","https://openalex.org/W6630493794","https://openalex.org/W6662227517","https://openalex.org/W6680972403","https://openalex.org/W6682398751","https://openalex.org/W6711851458"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W2150890698","https://openalex.org/W2162582511","https://openalex.org/W4245698648","https://openalex.org/W2401394187","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"This":[0],"article":[1],"describes":[2],"recent":[3],"results":[4,65,108],"obtained":[5],"for":[6],"two":[7],"challenging":[8],"large-vocabulary":[9],"speech":[10,120],"recognition":[11,50],"tasks":[12],"using":[13],"the":[14,60,71,96,99,110],"minimum":[15],"classification":[16],"error":[17],"(MCE)":[18],"approach":[19],"to":[20,31,57],"discriminative":[21,75],"training.":[22],"Weighted":[23],"finite":[24],"state":[25],"transducers":[26],"(WFSTs)":[27],"are":[28],"used":[29,55],"throughout":[30],"represent":[32],"correct":[33],"and":[34],"competing":[35],"string":[36],"candidates.":[37],"The":[38,64],"primary":[39],"task":[40,69],"examined":[41],"is":[42],"a":[43,124],"22":[44],"K":[45,112],"word,":[46],"real-world,":[47],"telephone-based":[48],"name":[49],"task.":[51],"Lattice-derived":[52],"WFSTs":[53],"were":[54],"successfully":[56],"speed":[58],"up":[59],"MCE":[61,82,92],"training":[62,93,125],"procedure.":[63],"of":[66,74,98,115,127,130],"this":[67],"difficult":[68],"follow":[70],"classic":[72],"picture":[73],"training:":[76],"small":[77],"acoustic":[78],"models":[79,87,101],"trained":[80,88],"with":[81,89,123],"outperform":[83],"much":[84],"larger":[85,100],"baseline":[86],"maximum":[90],"likelihood.":[91],"substantially":[94],"improves":[95],"performance":[97],"as":[102],"well.":[103],"We":[104],"also":[105],"present":[106],"preliminary":[107],"on":[109],"30":[111],"word":[113],"corpus":[114],"spontaneous":[116],"Japanese":[117],"(CSJ)":[118],"lecture":[119],"transcription":[121],"task,":[122],"set":[126],"190":[128],"hours":[129],"audio.":[131]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}