{"id":"https://openalex.org/W1568183767","doi":"https://doi.org/10.21437/interspeech.2007-430","title":"Phoneme confusions in human and automatic speech recognition","display_name":"Phoneme confusions in human and automatic speech recognition","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W1568183767","doi":"https://doi.org/10.21437/interspeech.2007-430","mag":"1568183767"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-430","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","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/A5067491941","display_name":"Bernd T. Meyer","orcid":"https://orcid.org/0000-0001-9190-2111"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bernd T. Meyer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070400670","display_name":"Matthias W\u00e4chter","orcid":"https://orcid.org/0000-0001-9212-1122"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthias W\u00e4chter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111469345","display_name":"Thomas Brand","orcid":"https://orcid.org/0000-0002-8740-8871"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Brand","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076869895","display_name":"Birger Kollmeier","orcid":"https://orcid.org/0000-0001-8584-4779"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Birger Kollmeier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4482,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.90174373,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1485","last_page":"1488"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9987999796867371,"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/T11309","display_name":"Music and Audio Processing","score":0.9918000102043152,"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/speech-recognition","display_name":"Speech recognition","score":0.8404841423034668},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7742048501968384},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7730169892311096},{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.6765551567077637},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.6042424440383911},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5200880765914917},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5125377178192139},{"id":"https://openalex.org/keywords/nonsense","display_name":"Nonsense","score":0.48926445841789246},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4496578872203827},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.43386948108673096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4088265895843506},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3895331621170044},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.06908458471298218}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8404841423034668},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7742048501968384},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730169892311096},{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.6765551567077637},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.6042424440383911},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5200880765914917},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5125377178192139},{"id":"https://openalex.org/C62923972","wikidata":"https://www.wikidata.org/wiki/Q600499","display_name":"Nonsense","level":3,"score":0.48926445841789246},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4496578872203827},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.43386948108673096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4088265895843506},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3895331621170044},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.06908458471298218},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2007-430","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.211.7808","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.211.7808","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://medi.uni-oldenburg.de/members/bernd/Meyer_Phoneme_Confusions_IS2007.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W184933960","https://openalex.org/W341270402","https://openalex.org/W1554887097","https://openalex.org/W1860981223","https://openalex.org/W2114827915","https://openalex.org/W2133815075","https://openalex.org/W2163680580"],"related_works":["https://openalex.org/W2036753972","https://openalex.org/W1996861825","https://openalex.org/W2497205885","https://openalex.org/W2079621619","https://openalex.org/W2046280377","https://openalex.org/W4388535697","https://openalex.org/W2036128733","https://openalex.org/W1976086899","https://openalex.org/W4387870978","https://openalex.org/W2953493266"],"abstract_inverted_index":{"A":[0],"comparison":[1],"between":[2],"automatic":[3,154],"speech":[4,9,56,152,155],"recognition":[5,10],"(ASR)":[6],"and":[7,21,28,73,115,124],"human":[8,52,151],"(HSR)":[11],"is":[12,88],"performed":[13],"as":[14,140],"prerequisite":[15],"for":[16,122],"identifying":[17],"sources":[18],"of":[19,41,47,94,100,108,133,143],"errors":[20],"improving":[22],"feature":[23],"extraction":[24],"in":[25],"ASR.":[26],"HSR":[27],"ASR":[29,109,123,134],"experiments":[30],"are":[31,49,58,65,85],"carried":[32],"out":[33],"with":[34,69,82],"the":[35,79,92,98,106,131,137,144],"same":[36,138],"logatome":[37],"database":[38],"which":[39,64,87],"consists":[40],"nonsense":[42],"syllables.":[43],"Two":[44],"different":[45,118],"kinds":[46],"signals":[48,81],"presented":[50],"to":[51,60,67,90],"listeners:":[53],"First,":[54],"noisy":[55],"samples":[57],"converted":[59],"Mel-frequency":[61],"cepstral":[62],"coefficients":[63],"resynthesized":[66],"speech,":[68],"information":[70,95,127],"about":[71],"voicing":[72],"fundamental":[74],"frequency":[75],"being":[76],"discarded.":[77],"Second,":[78],"original":[80],"added":[83],"noise":[84],"presented,":[86],"used":[89],"evaluate":[91],"loss":[93,128],"caused":[96,110],"by":[97,111,130,146],"process":[99],"resynthesis.":[101],"The":[102,126],"analysis":[103],"also":[104],"covers":[105],"degradation":[107],"dialect":[112],"or":[113],"accent":[114],"shows":[116],"that":[117],"error":[119],"patterns":[120],"emerge":[121],"HSR.":[125],"induced":[129],"calculation":[132],"features":[135],"has":[136],"effect":[139],"a":[141],"deteriation":[142],"SNR":[145],"10":[147],"dB.":[148],"Index":[149],"Terms:":[150],"recognition,":[153,156],"dialect,":[157],"accent,":[158],"phoneme":[159],"confusions,":[160],"MFCC":[161]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
