{"id":"https://openalex.org/W2102504831","doi":"https://doi.org/10.1109/icassp.1985.1168478","title":"Comparative study of several distortoin measures for speech recognition","display_name":"Comparative study of several distortoin measures for speech recognition","publication_year":2005,"publication_date":"2005-03-23","ids":{"openalex":"https://openalex.org/W2102504831","doi":"https://doi.org/10.1109/icassp.1985.1168478","mag":"2102504831"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.1985.1168478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1985.1168478","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/A5081391894","display_name":"N. Nocerino","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":"N. Nocerino","raw_affiliation_strings":["AT and T Bell Laboratories, Inc., Murray Hill, NJ, USA"],"raw_orcid":null,"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"],"raw_orcid":null,"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"],"raw_orcid":null,"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/A5069744359","display_name":"Dennis H. Klatt","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":"D. Klatt","raw_affiliation_strings":["AT and T Bell Laboratories, Inc., Murray Hill, NJ, USA"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":5.8352,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.96615687,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"25","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9944000244140625,"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/T10860","display_name":"Speech and Audio Processing","score":0.9926999807357788,"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/distortion","display_name":"Distortion (music)","score":0.7413603067398071},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6271030306816101},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.6136946678161621},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5614709854125977},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5472764372825623},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5255464315414429},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5032808184623718},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42529892921447754},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.42314955592155457},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3873707354068756},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.33334892988204956},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.10100150108337402},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09570014476776123},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07328441739082336}],"concepts":[{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.7413603067398071},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6271030306816101},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.6136946678161621},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5614709854125977},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5472764372825623},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5255464315414429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5032808184623718},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42529892921447754},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.42314955592155457},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3873707354068756},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.33334892988204956},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.10100150108337402},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09570014476776123},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07328441739082336},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.1985.1168478","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.1985.1168478","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1920160043","https://openalex.org/W1989337816","https://openalex.org/W2137089646","https://openalex.org/W2164240509"],"related_works":["https://openalex.org/W2347413598","https://openalex.org/W71572444","https://openalex.org/W1997383766","https://openalex.org/W2154472250","https://openalex.org/W2350336482","https://openalex.org/W2380251249","https://openalex.org/W2229352698","https://openalex.org/W2001283968","https://openalex.org/W2126960140","https://openalex.org/W2371038066"],"abstract_inverted_index":{"In":[0],"this":[1],"study":[2],"we":[3],"compared":[4],"several":[5],"different":[6],"spectral":[7],"distortion":[8,30,43,90,115,124,134,178],"measures":[9,91,116,125],"including":[10],"the":[11,14,19,23,32,38,51,68,83,127,132,137,142,149,152,160],"Itakura-Saito":[12],"(IS),":[13],"log":[15],"likelihood":[16,20,34],"ratio":[17,21,35],"(LLR),":[18],"(LR),":[22],"cepstral":[24],"(CEP),":[25],"and":[26,37,82,92,122,156],"two":[27],"perceptually":[28],"based":[29],"measures,":[31,44],"weighted":[33,39],"(WLR)":[36],"slope":[40],"metric":[41],"(WSM)":[42],"in":[45],"terms":[46],"of":[47,53,67,71,85,144,154],"their":[48,93],"effects":[49],"on":[50,97],"performance":[52],"a":[54,78],"standard":[55],"dynamic":[56],"time":[57],"warping":[58,81,165],"(DTW)":[59],"based,":[60],"isolated":[61],"word,":[62],"speech":[63],"recognizer.":[64],"Two":[65],"modifications":[66,94],"basic":[69],"forms":[70],"each":[72],"measure":[73,135,179],"were":[74,95],"also":[75],"investigated,":[76],"namely":[77],"Bark-scale":[79,163],"frequency":[80,164],"incorporation":[84],"suprasegmental":[86,145],"energy":[87,146],"information.":[88],"All":[89,113],"tested":[96],"an":[98],"alpha-digit":[99],"vocabulary,":[100],"4-talker,":[101],"telephone":[102],"recording":[103],"data":[104],"base.":[105],"The":[106,120,176],"results":[107],"can":[108],"be":[109],"summarized":[110],"as:":[111],"(1)":[112],"LPC-based":[114],"performed":[117],"reasonably":[118],"well.":[119],"LLR":[121],"WSM":[123],"gave":[126,136],"highest":[128],"recognition":[129,150],"accuracy,":[130],"while":[131],"IS":[133],"lowest":[138],"score;":[139],"(2)":[140],"Whereas":[141],"addition":[143],"information":[147],"helped":[148],"performance,":[151],"use":[153],"gain":[155],"absolute":[157],"loudness":[158],"degraded":[159],"performance;":[161],"(3)":[162],"did":[166,180],"not":[167,181],"perform":[168,182],"as":[169,171,183,185],"well":[170,184],"its":[172,186],"unwarped":[173],"counterpart;":[174],"(4)":[175],"WLR":[177],"unweighted":[187],"counterpart.":[188]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}