{"id":"https://openalex.org/W1571246086","doi":"https://doi.org/10.1109/icassp.1986.1168581","title":"Speaker-independent isolated word recognition using label histograms","display_name":"Speaker-independent isolated word recognition using label histograms","publication_year":2005,"publication_date":"2005-03-24","ids":{"openalex":"https://openalex.org/W1571246086","doi":"https://doi.org/10.1109/icassp.1986.1168581","mag":"1571246086"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1986.1168581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1986.1168581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5059528454","display_name":"Osaaki Watanuki","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"O. Watanuki","raw_affiliation_strings":["Science Institute, IBM Japan Limited, Japan"],"affiliations":[{"raw_affiliation_string":"Science Institute, IBM Japan Limited, Japan","institution_ids":["https://openalex.org/I4210145865"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110454630","display_name":"T. Kaneko","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145865","display_name":"IBM Research - Tokyo","ror":"https://ror.org/04915qk43","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210145865"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Kaneko","raw_affiliation_strings":["Science Institute, IBM Japan Limited, Japan"],"affiliations":[{"raw_affiliation_string":"Science Institute, IBM Japan Limited, Japan","institution_ids":["https://openalex.org/I4210145865"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059528454"],"corresponding_institution_ids":["https://openalex.org/I4210145865"],"apc_list":null,"apc_paid":null,"fwci":0.4388,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71748241,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":null,"first_page":"2679","last_page":"2682"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9954000115394592,"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":0.9954000115394592,"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":0.9887999892234802,"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/T12205","display_name":"Time Series Analysis and Forecasting","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":0.8260451555252075},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7373285293579102},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7234125137329102},{"id":"https://openalex.org/keywords/histogram","display_name":"Histogram","score":0.7068222761154175},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6746410727500916},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6506911516189575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6068077087402344},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5878037810325623},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.5678741335868835},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.5517369508743286},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5383170247077942},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4784024655818939},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45495525002479553},{"id":"https://openalex.org/keywords/signature-recognition","display_name":"Signature recognition","score":0.41583770513534546},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.41536450386047363},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.26305660605430603},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19030869007110596},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11489534378051758},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09442126750946045}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8260451555252075},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7373285293579102},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7234125137329102},{"id":"https://openalex.org/C53533937","wikidata":"https://www.wikidata.org/wiki/Q185020","display_name":"Histogram","level":3,"score":0.7068222761154175},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6746410727500916},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6506911516189575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6068077087402344},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5878037810325623},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.5678741335868835},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.5517369508743286},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5383170247077942},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4784024655818939},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45495525002479553},{"id":"https://openalex.org/C74370796","wikidata":"https://www.wikidata.org/wiki/Q15924863","display_name":"Signature recognition","level":3,"score":0.41583770513534546},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.41536450386047363},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26305660605430603},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19030869007110596},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11489534378051758},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09442126750946045},{"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1986.1168581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1986.1168581","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1539742940","https://openalex.org/W1990005915","https://openalex.org/W2021760654","https://openalex.org/W2097012520","https://openalex.org/W2124336637","https://openalex.org/W2137309058"],"related_works":["https://openalex.org/W2167131998","https://openalex.org/W1992908141","https://openalex.org/W1980930823","https://openalex.org/W4205357519","https://openalex.org/W2389799231","https://openalex.org/W2124406344","https://openalex.org/W2367317189","https://openalex.org/W1964909833","https://openalex.org/W2148167314","https://openalex.org/W1985887223"],"abstract_inverted_index":{"In":[0,31,69],"this":[1,103],"paper,":[2],"a":[3,120],"simple":[4],"and":[5,37,85,118],"fast":[6],"method":[7,16,104,109],"for":[8],"speaker-independent":[9],"isolated":[10],"word":[11,77],"recognition":[12,114,121],"is":[13,17,78,88,105,110],"presented.":[14],"This":[15,108],"regarded":[18],"as":[19],"simplification":[20],"of":[21,53,74,102,115,129],"the":[22,26,32,50,66,71,86,91,99,113,130],"approach":[23],"based":[24],"on":[25],"Hidden":[27],"Markov":[28],"Model":[29],"(HMM).":[30],"proposed":[33],"method,":[34],"all":[35],"training":[36,67],"decoding":[38],"data":[39],"are":[40,63],"transformed":[41],"into":[42,55,81],"label":[43,51,61,72],"strings":[44,52],"by":[45],"vector":[46],"quantization.":[47],"By":[48],"segmenting":[49],"utterances":[54],"N":[56,83],"pieces":[57],"with":[58,90],"equal":[59,82],"duration,":[60],"histograms":[62],"computed":[64,89],"in":[65],"mode.":[68],"recognition,":[70],"string":[73],"an":[75],"input":[76],"also":[79],"divided":[80],"segments,":[84],"likelihood":[87],"corresponding":[92],"histogram.":[93],"It":[94],"will":[95],"be":[96],"shown":[97],"that":[98,128],"computational":[100],"cost":[101],"relatively":[106],"low.":[107],"applied":[111],"to":[112,124],"32-Japanese-word":[116],"vocabulary,":[117],"achieved":[119],"accuracy":[122],"comparable":[123],"or":[125],"better":[126],"than":[127],"conventional":[131],"approaches.":[132]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}