{"id":"https://openalex.org/W2010299594","doi":"https://doi.org/10.1109/acssc.2012.6489305","title":"Exploiting sparsity in stranded hidden Markov models for automatic speech recognition","display_name":"Exploiting sparsity in stranded hidden Markov models for automatic speech recognition","publication_year":2012,"publication_date":"2012-11-01","ids":{"openalex":"https://openalex.org/W2010299594","doi":"https://doi.org/10.1109/acssc.2012.6489305","mag":"2010299594"},"language":"en","primary_location":{"id":"doi:10.1109/acssc.2012.6489305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2012.6489305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 Conference Record of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR)","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/A5100702071","display_name":"Yong Zhao","orcid":"https://orcid.org/0000-0003-2644-952X"},"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":"Yong Zhao","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, 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":["Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, 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":0.5203,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60211204,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1623","last_page":"1625"},"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":0.9995999932289124,"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":0.9987000226974487,"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":0.9355695247650146},{"id":"https://openalex.org/keywords/maximum-a-posteriori-estimation","display_name":"Maximum a posteriori estimation","score":0.7763438820838928},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6785323023796082},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6702591180801392},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6677905321121216},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5909460783004761},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5789120197296143},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5429226756095886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5309345722198486},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5276196002960205},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5002646446228027},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4631153643131256},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33358293771743774},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.26322007179260254},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2304837703704834}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9355695247650146},{"id":"https://openalex.org/C9810830","wikidata":"https://www.wikidata.org/wiki/Q635384","display_name":"Maximum a posteriori estimation","level":3,"score":0.7763438820838928},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6785323023796082},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6702591180801392},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6677905321121216},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5909460783004761},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5789120197296143},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5429226756095886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5309345722198486},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5276196002960205},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5002646446228027},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4631153643131256},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33358293771743774},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.26322007179260254},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2304837703704834},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/acssc.2012.6489305","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2012.6489305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 Conference Record of the Forty Sixth Asilomar Conference on Signals, Systems and Computers (ASILOMAR)","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":12,"referenced_works":["https://openalex.org/W1551198852","https://openalex.org/W1833981795","https://openalex.org/W2051347452","https://openalex.org/W2068728923","https://openalex.org/W2096044236","https://openalex.org/W2107361128","https://openalex.org/W2108840068","https://openalex.org/W2122836549","https://openalex.org/W2140669298","https://openalex.org/W2151484683","https://openalex.org/W6632976298","https://openalex.org/W6678298469"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W1839961359","https://openalex.org/W1595191759","https://openalex.org/W2160650576","https://openalex.org/W2075146114","https://openalex.org/W2010299594","https://openalex.org/W2100805585"],"abstract_inverted_index":{"We":[0],"have":[1],"recently":[2],"proposed":[3],"the":[4,19,24,29,32,51,58,74,89,96,119],"stranded":[5,25,59,75],"HMM":[6,26,60,76],"to":[7,18,61,72],"achieve":[8],"a":[9,91,105,115],"more":[10],"accurate":[11],"representation":[12],"of":[13,43,95,118],"heterogeneous":[14],"data.":[15],"As":[16],"opposed":[17],"regular":[20],"Gaussian":[21],"mixture":[22,33,38,97],"HMM,":[23],"explicitly":[27],"models":[28],"relationships":[30],"among":[31,37],"components.":[34],"The":[35,100],"transitions":[36],"components":[39],"encode":[40],"possible":[41],"trajectories":[42],"acoustic":[44],"features":[45],"for":[46,57],"speech":[47],"units.":[48],"Accurately":[49],"representing":[50],"underlying":[52],"transition":[53,98],"structure":[54,77],"is":[55],"crucial":[56],"produce":[62],"an":[63],"optimal":[64],"recognition":[65,120],"performance.":[66],"In":[67,82],"this":[68],"paper,":[69],"we":[70],"propose":[71],"learn":[73],"by":[78],"imposing":[79],"sparsity":[80,110],"constraints.":[81],"particular,":[83],"entropic":[84],"priors":[85],"are":[86],"incorporated":[87],"in":[88,108],"maximum":[90],"posteriori":[92],"(MAP)":[93],"estimation":[94],"matrices.":[99],"experimental":[101],"results":[102],"showed":[103],"that":[104],"significant":[106],"improvement":[107],"model":[109],"can":[111],"be":[112],"obtained":[113],"with":[114],"slight":[116],"sacrifice":[117],"accuracy.":[121]},"counts_by_year":[{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}