{"id":"https://openalex.org/W2106959768","doi":"https://doi.org/10.1109/icassp.2012.6288845","title":"Bag Of ARCS: New representation of speech segment features based on finite state machines","display_name":"Bag Of ARCS: New representation of speech segment features based on finite state machines","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2106959768","doi":"https://doi.org/10.1109/icassp.2012.6288845","mag":"2106959768"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288845","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":"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/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"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"]},{"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","US"],"is_corresponding":true,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge Massachusetts, USA","NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge Massachusetts, 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/A5102252420","display_name":"Yotaro Kubo","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":false,"raw_author_name":"Yotaro Kubo","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"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/A5109336432","display_name":"Takanobu Oba","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":false,"raw_author_name":"Takanobu Oba","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"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/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"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":"Takaaki Hori","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Kyoto, Japan"],"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"],"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":5,"corresponding_author_ids":["https://openalex.org/A5001291873"],"corresponding_institution_ids":["https://openalex.org/I2251713219","https://openalex.org/I4210159266"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12521475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"4201","last_page":"4204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.730505108833313},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5812954306602478},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5557258129119873},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5447677969932556},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5300395488739014},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5211567878723145},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48457610607147217},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46842801570892334},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4644837975502014},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.4434347152709961},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.44074591994285583},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43913161754608154},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43118321895599365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40053707361221313},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25212085247039795},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15111255645751953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.730505108833313},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5812954306602478},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5557258129119873},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5447677969932556},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5300395488739014},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5211567878723145},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48457610607147217},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46842801570892334},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4644837975502014},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.4434347152709961},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.44074591994285583},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43913161754608154},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43118321895599365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40053707361221313},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25212085247039795},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15111255645751953},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2012.6288845","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288845","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W81231479","https://openalex.org/W1604792744","https://openalex.org/W1644652583","https://openalex.org/W1880262756","https://openalex.org/W1895481600","https://openalex.org/W1924689489","https://openalex.org/W1984196678","https://openalex.org/W2008652694","https://openalex.org/W2046932483","https://openalex.org/W2092062917","https://openalex.org/W2134861448","https://openalex.org/W2138889249","https://openalex.org/W2144252361","https://openalex.org/W2161195767","https://openalex.org/W2167270514","https://openalex.org/W2169384404","https://openalex.org/W2336725036","https://openalex.org/W3007254004","https://openalex.org/W4237791300","https://openalex.org/W6601563604","https://openalex.org/W6603242303","https://openalex.org/W6636890138","https://openalex.org/W6683794572","https://openalex.org/W6684930139"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W2333799855","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2351687372","https://openalex.org/W2314871050","https://openalex.org/W2383414243"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,23,31,64,77,96,138,157],"new":[4],"feature":[5],"representation,":[6],"Bag":[7,38],"Of":[8,39],"Arcs":[9],"(BOA)":[10],"for":[11,27,179,211],"speech":[12,15,53],"segments.":[13,54],"A":[14,55],"segment":[16],"in":[17,30,91,184,189,198],"BOA":[18,43,60,68,87,119,212],"is":[19,61,70],"simply":[20],"represented":[21],"as":[22],"set":[24],"of":[25,47,76,95,118,140,175,207],"counts":[26,117],"unique":[28],"arcs":[29],"finite":[32],"state":[33],"machine.":[34],"Similar":[35],"to":[36,58,73,143,159],"the":[37,45,67,74,92,116,124,145,151,164,173,176],"Words":[40],"model":[41],"(BOW),":[42],"disregards":[44],"order":[46],"arcs,":[48],"and":[49,100,109,129,137,154,188],"thus,":[50],"efficiently":[51],"models":[52],"strong":[56],"motivation":[57],"use":[59],"provided":[62],"by":[63,122,193,213],"fact":[65],"that":[66],"representation":[69],"tightly":[71],"connected":[72],"output":[75,127],"Weighted":[78],"Finite":[79],"State":[80],"Transducer":[81],"(WFST)":[82],"based":[83],"ASR":[84,98,152,181],"decoder.":[85],"Thus,":[86],"directly":[88],"represents":[89],"elements":[90],"search":[93],"network":[94],"WFST-based":[97],"decoder,":[99],"can":[101,149],"include":[102],"information":[103],"about":[104],"context-dependent":[105],"HMM":[106],"topologies,":[107],"lexicons,":[108],"back-off":[110],"smoothed":[111],"n-gram":[112],"networks.":[113,170],"In":[114],"addition,":[115],"are":[120],"accumulated":[121],"using":[123,214],"WFST":[125,169],"decoder":[126,153,165],"directly,":[128],"we":[130,148],"do":[131],"not":[132],"require":[133],"an":[134],"additional":[135],"overhead":[136],"change":[139],"decoding":[141],"algorithms":[142],"extract":[144,160],"features.":[146],"Consequently,":[147],"combine":[150],"post-processing":[155,182],"without":[156],"process":[158],"word":[161],"features":[162],"from":[163,200],"outputs":[166],"or":[167],"re-compiling":[168],"We":[171,203],"show":[172,205],"effectiveness":[174],"proposed":[177],"approach":[178],"some":[180],"applications":[183],"utterance":[185],"classification":[186],"experiments,":[187],"speaker":[190],"adaptation":[191],"experiments":[192],"achieving":[194],"absolute":[195],"1%":[196],"improvement":[197],"WER":[199],"baseline":[201],"results.":[202],"also":[204],"examples":[206],"latent":[208,215],"semantic":[209],"analysis":[210],"Dirichlet":[216],"allocation.":[217]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}