{"id":"https://openalex.org/W1489183891","doi":"https://doi.org/10.21437/eurospeech.2003-179","title":"Extraction methods of voicing feature for robust speech recognition","display_name":"Extraction methods of voicing feature for robust speech recognition","publication_year":2003,"publication_date":"2003-09-01","ids":{"openalex":"https://openalex.org/W1489183891","doi":"https://doi.org/10.21437/eurospeech.2003-179","mag":"1489183891"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.2003-179","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","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/A5038721535","display_name":"Andr\u00e1s Zolnay","orcid":"https://orcid.org/0000-0001-8476-9092"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Andras Zolnay","raw_affiliation_strings":["[Rwth Aachen University]"],"affiliations":[{"raw_affiliation_string":"[Rwth Aachen University]","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088968292","display_name":"Ralf Schl\u00fcter","orcid":"https://orcid.org/0000-0003-2839-9247"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schluter","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Lehrstuhl f\u00fcr Informatik VI, Computer Science Department RWTH Aachen -University of Technology 52056 Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Lehrstuhl f\u00fcr Informatik VI, Computer Science Department RWTH Aachen -University of Technology 52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112501010","display_name":"Hermann Ney","orcid":null},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hermann Ney","raw_affiliation_strings":["Human Language Technology and Pattern Recognition Lehrstuhl f\u00fcr Informatik VI, Computer Science Department RWTH Aachen -University of Technology 52056 Aachen, Germany"],"affiliations":[{"raw_affiliation_string":"Human Language Technology and Pattern Recognition Lehrstuhl f\u00fcr Informatik VI, Computer Science Department RWTH Aachen -University of Technology 52056 Aachen, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038721535"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":3.2757,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.92005549,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"497","last_page":"500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9987000226974487,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9842000007629395,"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/voice","display_name":"Voice","score":0.9234457015991211},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8302851319313049},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7490710616111755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7133013010025024},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5712373852729797},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5387758612632751},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.5285849571228027},{"id":"https://openalex.org/keywords/autocorrelation","display_name":"Autocorrelation","score":0.5279024243354797},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5174568295478821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4787446856498718},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4766048789024353},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.46493810415267944},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.45971348881721497},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19554203748703003},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.10229259729385376},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.06597143411636353}],"concepts":[{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.9234457015991211},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8302851319313049},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7490710616111755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7133013010025024},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5712373852729797},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5387758612632751},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.5285849571228027},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.5279024243354797},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5174568295478821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4787446856498718},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4766048789024353},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.46493810415267944},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.45971348881721497},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19554203748703003},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10229259729385376},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.06597143411636353},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/eurospeech.2003-179","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.2003-179","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"8th European Conference on Speech Communication and Technology (Eurospeech 2003)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.14.6313","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.14.6313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/PostScript/InterneArbeiten/Zolnay_Eurospeech_2003.ps","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.310.1485","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.310.1485","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-i6.informatik.rwth-aachen.de/publications/download/400/ZolnayAndrasSchl%7Bu%7DterRalfNeyHermann--ExtractionMethodsofVoicingFeatureforRobustSpeechRecognition--2003.pdf","raw_type":"text"},{"id":"pmh:oai:publications.rwth-aachen.de:113414","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/113414","pdf_url":null,"source":{"id":"https://openalex.org/S4306401362","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Eurospeech 2003 proceedings : 8th European Conference on Speech Communication and Technology ; September 1 - 4, 2003, Geneva, Switzerland ; [INTERSPEECH 2003] / [International Speech Communication Association]. - Vol. 1<br/>8. European Conference on Speech Communication and Technology, Eurospeech 2003, Geneva, Switzerland, 2003-09-01 - 2003-09-04","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W45838861","https://openalex.org/W89460608","https://openalex.org/W1560013842","https://openalex.org/W1854414011","https://openalex.org/W2036039581","https://openalex.org/W2465080433","https://openalex.org/W3094114204"],"related_works":["https://openalex.org/W2036753972","https://openalex.org/W1996861825","https://openalex.org/W2079621619","https://openalex.org/W2046280377","https://openalex.org/W4388535697","https://openalex.org/W2497205885","https://openalex.org/W2036128733","https://openalex.org/W1976086899","https://openalex.org/W4285526294","https://openalex.org/W1494724239"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"three":[3,87],"different":[4,88],"voicing":[5,48,54,89],"features":[6,12],"are":[7],"studied":[8],"as":[9],"additional":[10],"acoustic":[11],"for":[13,49],"continuous":[14],"speech":[15],"recognition.":[16],"The":[17,42,53,86],"harmonic":[18],"product":[19],"spectrum":[20],"based":[21,36],"feature":[22],"is":[23],"extracted":[24],"in":[25,39,95,98,133],"frequency":[26],"domain":[27],"while":[28],"the":[29,32,59,72,108,118,127,134],"autocorrelation":[30],"and":[31,82,111],"average":[33],"magnitude":[34],"difference":[35],"methods":[37],"work":[38],"time":[40,51],"domain.":[41],"algorithms":[43],"produce":[44],"a":[45],"measure":[46,55],"of":[47,103,113,131],"each":[50],"frame.":[52],"was":[56],"combined":[57,91],"with":[58,92,126],"standard":[60],"Mel":[61],"Frequency":[62],"Cepstral":[63],"Coefficients":[64],"(MFCC)":[65],"using":[66,123],"linear":[67],"discriminant":[68],"analysis":[69],"to":[70,105,115,122],"choose":[71],"most":[73],"relevant":[74],"features.":[75],"Experiments":[76],"have":[77],"been":[78],"performed":[79],"on":[80,107,117],"small":[81],"large":[83],"vocabulary":[84],"tasks.":[85],"measures":[90],"MFCCs":[93],"resulted":[94],"similar":[96],"improvements":[97,102,112],"word":[99],"error":[100],"rate:":[101],"up":[104,114],"14%":[106],"smallvocabulary":[109],"task":[110,120],"6%":[116],"largevocabulary":[119],"relative":[121],"MFCC":[124],"alone":[125],"same":[128],"overall":[129],"number":[130],"parameters":[132],"system.":[135]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}