{"id":"https://openalex.org/W2153254780","doi":"https://doi.org/10.1186/1687-4722-2012-10","title":"Decision tree-based acoustic models for speech recognition","display_name":"Decision tree-based acoustic models for speech recognition","publication_year":2012,"publication_date":"2012-02-17","ids":{"openalex":"https://openalex.org/W2153254780","doi":"https://doi.org/10.1186/1687-4722-2012-10","mag":"2153254780"},"language":"en","primary_location":{"id":"doi:10.1186/1687-4722-2012-10","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-10","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-10","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-10","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112250968","display_name":"Masami Akamine","orcid":null},"institutions":[{"id":"https://openalex.org/I1292669757","display_name":"Toshiba (Japan)","ror":"https://ror.org/0326v3z14","country_code":"JP","type":"company","lineage":["https://openalex.org/I1292669757"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masami Akamine","raw_affiliation_strings":["Toshiba Corporate R&D Center, 1, Komukai Toshiba, Saiwai, Kawasaki, 212-8582, Japan"],"affiliations":[{"raw_affiliation_string":"Toshiba Corporate R&D Center, 1, Komukai Toshiba, Saiwai, Kawasaki, 212-8582, Japan","institution_ids":["https://openalex.org/I1292669757"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063781689","display_name":"Jitendra Ajmera","orcid":null},"institutions":[{"id":"https://openalex.org/I4210103279","display_name":"IBM Research - India","ror":"https://ror.org/014wt7r80","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210103279","https://openalex.org/I4210114115"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Jitendra Ajmera","raw_affiliation_strings":["IBM Research Lab., 4 Block C, Institutional Area, Vasant Kunj, New Delhi, 110070, India"],"affiliations":[{"raw_affiliation_string":"IBM Research Lab., 4 Block C, Institutional Area, Vasant Kunj, New Delhi, 110070, India","institution_ids":["https://openalex.org/I4210103279"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112250968"],"corresponding_institution_ids":["https://openalex.org/I1292669757"],"apc_list":{"value":1115,"currency":"GBP","value_usd":1367},"apc_paid":{"value":1115,"currency":"GBP","value_usd":1367},"fwci":0.4281,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.73480079,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"2012","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9976000189781189,"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":0.9976000189781189,"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":0.9972000122070312,"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/T10860","display_name":"Speech and Audio Processing","score":0.9807000160217285,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8353028297424316},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7858961224555969},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6919646859169006},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.6757357120513916},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6662177443504333},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6566548347473145},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5412755012512207},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5350009202957153},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.5139179229736328},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5018908977508545},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4978201389312744},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4920777678489685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45660853385925293},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4374648630619049},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.4308141767978668},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4164994955062866},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38156113028526306},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.22054517269134521},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.20654717087745667},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10277888178825378},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09874555468559265}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8353028297424316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7858961224555969},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6919646859169006},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6757357120513916},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6662177443504333},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6566548347473145},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5412755012512207},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5350009202957153},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.5139179229736328},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5018908977508545},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4978201389312744},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4920777678489685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45660853385925293},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4374648630619049},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.4308141767978668},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4164994955062866},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38156113028526306},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.22054517269134521},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.20654717087745667},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10277888178825378},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09874555468559265},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1186/1687-4722-2012-10","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-10","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-10","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1186/1687-4722-2012-10","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1687-4722-2012-10","pdf_url":"https://asmp-eurasipjournals.springeropen.com/counter/pdf/10.1186/1687-4722-2012-10","source":{"id":"https://openalex.org/S19605986","display_name":"EURASIP Journal on Audio Speech and Music Processing","issn_l":"1687-4714","issn":["1687-4714","1687-4722"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"EURASIP Journal on Audio, Speech, and Music Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2153254780.pdf","grobid_xml":"https://content.openalex.org/works/W2153254780.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W106637968","https://openalex.org/W146710046","https://openalex.org/W179814313","https://openalex.org/W272615811","https://openalex.org/W1594031697","https://openalex.org/W2002919652","https://openalex.org/W2122028591","https://openalex.org/W2142183264","https://openalex.org/W2156255174","https://openalex.org/W2162818124","https://openalex.org/W2415511073","https://openalex.org/W2607893089","https://openalex.org/W2799061466","https://openalex.org/W2805889152","https://openalex.org/W3085162807","https://openalex.org/W3143835353","https://openalex.org/W4244494905","https://openalex.org/W6611528966"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W4285282705","https://openalex.org/W2075383893","https://openalex.org/W1510894296","https://openalex.org/W2134386692","https://openalex.org/W2082284720","https://openalex.org/W2194396582","https://openalex.org/W2116722627"],"abstract_inverted_index":{"This":[0,64,130],"article":[1,65],"proposes":[2],"a":[3,24,31,37],"new":[4],"acoustic":[5,94,114,128],"model":[6,28,90],"using":[7],"decision":[8],"trees":[9],"(DTs)":[10],"as":[11,43,116],"replacements":[12],"for":[13,23,70,98],"Gaussian":[14],"mixture":[15],"models":[16,115,120,135],"(GMM)":[17],"to":[18,88,125],"compute":[19],"the":[20,51,71,99,110,133],"observation":[21],"likelihoods":[22],"given":[25],"hidden":[26],"Markov":[27],"state":[29],"in":[30],"speech":[32,76],"recognition":[33],"system.":[34],"DTs":[35,69,87],"have":[36,82,136],"number":[38,52],"of":[39,55,73,112],"advantageous":[40],"properties,":[41],"such":[42],"that":[44,58,105,132],"they":[45,59],"do":[46],"not":[47],"impose":[48],"restrictions":[49],"on":[50],"or":[53],"types":[54],"features,":[56],"and":[57,67,79,92],"automatically":[60],"perform":[61],"feature":[62],"selection.":[63],"explores":[66],"exploits":[68],"purpose":[72],"large":[74],"vocabulary":[75],"recognition.":[77],"Equal":[78],"decoding":[80],"questions":[81],"newly":[83],"been":[84],"introduced":[85],"into":[86],"directly":[89],"gender-":[91],"context-dependent":[93],"space.":[95],"Experimental":[96],"results":[97],"5k":[100],"ARPA":[101],"wall-street-journal":[102],"task":[103],"show":[104],"context":[106,141],"information":[107],"significantly":[108],"improves":[109],"performance":[111],"DT-based":[113,119],"expected.":[117],"Context-dependent":[118],"are":[121],"highly":[122],"compact":[123],"compared":[124],"conventional":[126],"GMM-based":[127],"models.":[129],"means":[131],"proposed":[134],"effective":[137],"data-sharing":[138],"across":[139],"various":[140],"classes.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}