{"id":"https://openalex.org/W2125298055","doi":"https://doi.org/10.1109/icassp.1985.1168317","title":"An efficient vector-quantization preprocessor for speaker independent isolated word recognition","display_name":"An efficient vector-quantization preprocessor for speaker independent isolated word recognition","publication_year":2005,"publication_date":"2005-03-23","ids":{"openalex":"https://openalex.org/W2125298055","doi":"https://doi.org/10.1109/icassp.1985.1168317","mag":"2125298055"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1985.1168317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1985.1168317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '85. 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/A5029057426","display_name":"K. C. Pan","orcid":"https://orcid.org/0009-0006-5499-4022"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"K. Pan","raw_affiliation_strings":["AT and T Bell Laboratories, Inc., Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Bell Laboratories, Inc., Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"F. Soong","raw_affiliation_strings":["AT and T Bell Laboratories, Inc., Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Bell Laboratories, Inc., Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110218997","display_name":"L. R. Rabiner","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L. Rabiner","raw_affiliation_strings":["AT and T Bell Laboratories, Inc., Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Bell Laboratories, Inc., Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035653508","display_name":"A. Bergh","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A. Bergh","raw_affiliation_strings":["AT and T Bell Laboratories, Inc., Murray Hill, NJ, USA"],"affiliations":[{"raw_affiliation_string":"AT and T Bell Laboratories, Inc., Murray Hill, NJ, USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029057426"],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":0.8812,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.77235531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"10","issue":null,"first_page":"874","last_page":"877"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9932000041007996,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/codebook","display_name":"Codebook","score":0.8679111003875732},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7574297189712524},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.7361700534820557},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6938974857330322},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6864098906517029},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6514297723770142},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6293321847915649},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5760701894760132},{"id":"https://openalex.org/keywords/linde\u2013buzo\u2013gray-algorithm","display_name":"Linde\u2013Buzo\u2013Gray algorithm","score":0.47942155599594116},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42807650566101074},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.4263659119606018},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.42001497745513916},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3569563329219818},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2130119800567627},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14553159475326538},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08678865432739258}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8679111003875732},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7574297189712524},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.7361700534820557},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6938974857330322},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6864098906517029},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6514297723770142},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6293321847915649},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5760701894760132},{"id":"https://openalex.org/C93372532","wikidata":"https://www.wikidata.org/wiki/Q6552455","display_name":"Linde\u2013Buzo\u2013Gray algorithm","level":3,"score":0.47942155599594116},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42807650566101074},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.4263659119606018},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.42001497745513916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3569563329219818},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2130119800567627},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14553159475326538},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08678865432739258},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1985.1168317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1985.1168317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP '85. IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1914448748","https://openalex.org/W2021760654","https://openalex.org/W2028088067","https://openalex.org/W2045123594","https://openalex.org/W2046316417","https://openalex.org/W2112465852","https://openalex.org/W2134383396","https://openalex.org/W2163904446"],"related_works":["https://openalex.org/W2017514583","https://openalex.org/W2352648934","https://openalex.org/W2391875658","https://openalex.org/W2100120615","https://openalex.org/W1929869830","https://openalex.org/W2017401491","https://openalex.org/W2387054321","https://openalex.org/W2158612577","https://openalex.org/W2148772884","https://openalex.org/W1681061148"],"abstract_inverted_index":{"Recently":[0],"a":[1,21,35,82,95,182,237,264],"new":[2],"structure":[3,175,187],"for":[4,25,124,147,184,205,242],"isolated":[5],"word":[6,27,43,57,88,105],"recognition":[7,148,174],"was":[8,31,70],"proposed":[9,74,173,252],"based":[10,33],"on":[11,34,112,257,263],"the":[12,29,50,53,56,59,73,76,100,103,114,118,128,132,138,145,154,157,169,172,189,196,201,209,214,221,225,227,232,246,251,259],"ideas":[13],"of":[14,38,41,117,134,156,171,200,203,231,250,266],"vector":[15,207],"quantization":[16,63],"(VQ).":[17],"In":[18,49,72,194,224],"this":[19,180],"scheme":[20],"separate":[22],"VQ":[23,140,158,233],"codebook,":[24],"each":[26,42,206,243],"in":[28,58,137,150,208,245],"vocabulary,":[30,261],"designed,":[32],"training":[36,216],"sequence":[37,217],"several":[39],"tokens":[40],"by":[44,113],"one":[45],"or":[46],"more":[47],"talkers.":[48],"original":[51],"implementation,":[52,75],"recognizer":[54,253],"chose":[55],"vocabulary":[60,146,265],"whose":[61,90],"average":[62],"distortion":[64,91],"(according":[65],"to":[66,86,160,219],"its":[67],"particular":[68],"codebook)":[69],"minimum.":[71],"word-based":[77,139],"VQ's":[78],"are":[79,93,110],"used":[80,218],"as":[81,144],"front":[83],"end":[84],"preprocessor":[85,190],"eliminate":[87],"candidates":[89,106],"scores":[92],"large;":[94],"DTW":[96],"processor":[97,159],"then":[98],"resolves":[99],"choice":[101],"among":[102,162],"remaining":[104],"(i.e.":[107],"those":[108],"which":[109],"passed":[111],"preprocessor).":[115],"Both":[116],"above":[119],"schemes":[120],"work":[121],"very":[122],"well":[123],"small":[125],"vocabularies;":[126],"however":[127],"major":[129],"flaw":[130],"is":[131,191,211,234],"lack":[133],"temporal":[135,186,239],"information":[136],"processor.":[141],"As":[142],"such,":[143],"grows":[149],"size":[151],"and":[152,168,262],"complexity,":[153],"ability":[155],"resolve":[161],"similar":[163],"sounding":[164],"words":[165],"decreases":[166],"dramatically,":[167],"effectiveness":[170],"similarly":[176],"decreases.":[177],"To":[178],"alleviate":[179],"difficulty":[181],"technique":[183],"incorporating":[185],"into":[188],"also":[192],"proposed.":[193],"particular,":[195],"probability":[197],"density":[198],"function":[199],"time":[202],"occurrence":[204],"codebook":[210,222],"estimated":[212],"from":[213],"same":[215],"derive":[220],"vectors.":[223],"recognizer,":[226],"spectral":[228],"distance":[229,240],"score":[230],"combined":[235],"with":[236],"(scaled)":[238],"score,":[241],"frame":[244],"word.":[247],"An":[248],"evaluation":[249],"showed":[254],"good":[255],"performance":[256],"both":[258],"digits":[260],"129":[267],"airlines":[268],"terms.":[269]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}