{"id":"https://openalex.org/W2116696053","doi":"https://doi.org/10.1109/icassp.2005.1415135","title":"DWT-based phonetic groups classification using neural networks","display_name":"DWT-based phonetic groups classification using neural networks","publication_year":2006,"publication_date":"2006-09-22","ids":{"openalex":"https://openalex.org/W2116696053","doi":"https://doi.org/10.1109/icassp.2005.1415135","mag":"2116696053"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5012795098","display_name":"Tuan Van Pham","orcid":"https://orcid.org/0000-0002-9225-0191"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"T.V. Pham","raw_affiliation_strings":["Signal Process. & Speech Commun. Lab., Technische Univ. Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Process. & Speech Commun. Lab., Technische Univ. Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071861893","display_name":"Gernot Kubin","orcid":"https://orcid.org/0000-0002-8420-6051"},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"G. Kubin","raw_affiliation_strings":["Signal Processing and Speech Communication Laboratory, University of Technology, Graz, Austria","Signal Process. & Speech Commun. Lab., Technische Univ. Graz, Austria"],"affiliations":[{"raw_affiliation_string":"Signal Processing and Speech Communication Laboratory, University of Technology, Graz, Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"Signal Process. & Speech Commun. Lab., Technische Univ. Graz, Austria","institution_ids":["https://openalex.org/I4092182"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012795098"],"corresponding_institution_ids":["https://openalex.org/I4092182"],"apc_list":null,"apc_paid":null,"fwci":1.5902,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.82874001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I/401","last_page":"I/404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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/T10320","display_name":"Neural Networks and Applications","score":0.9977999925613403,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.994700014591217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7539570331573486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7410658001899719},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6730911731719971},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.5980886816978455},{"id":"https://openalex.org/keywords/consonant","display_name":"Consonant","score":0.585243284702301},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5411360263824463},{"id":"https://openalex.org/keywords/discrete-wavelet-transform","display_name":"Discrete wavelet transform","score":0.5016350746154785},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49743035435676575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49729302525520325},{"id":"https://openalex.org/keywords/feedforward-neural-network","display_name":"Feedforward neural network","score":0.47411754727363586},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.42104077339172363},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4115258455276489},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.4022265672683716}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7539570331573486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7410658001899719},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6730911731719971},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.5980886816978455},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.585243284702301},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5411360263824463},{"id":"https://openalex.org/C46286280","wikidata":"https://www.wikidata.org/wiki/Q2414958","display_name":"Discrete wavelet transform","level":4,"score":0.5016350746154785},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49743035435676575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49729302525520325},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.47411754727363586},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.42104077339172363},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4115258455276489},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.4022265672683716}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W132712915","https://openalex.org/W1985836220","https://openalex.org/W2019661654","https://openalex.org/W2130382378","https://openalex.org/W2138168847","https://openalex.org/W2151984047","https://openalex.org/W2154138336","https://openalex.org/W6738852829"],"related_works":["https://openalex.org/W1964706935","https://openalex.org/W2020946215","https://openalex.org/W2801025542","https://openalex.org/W1966580183","https://openalex.org/W2159095556","https://openalex.org/W2083136263","https://openalex.org/W4213283234","https://openalex.org/W4252296115","https://openalex.org/W2373394249","https://openalex.org/W1989026474"],"abstract_inverted_index":{"This":[0],"paper":[1,68],"presents":[2],"an":[3],"improvement":[4],"of":[5],"the":[6,84],"discrete":[7],"wavelet":[8],"transform":[9],"(DWT)-based":[10],"phonetic":[11],"classification":[12],"algorithm":[13,80],"by":[14,42],"using":[15],"neural":[16],"networks":[17],"(NN)":[18],"to":[19,49,71,92],"learn":[20],"optimal":[21],"thresholds":[22,64],"for":[23],"speech":[24,37],"classification.":[25],"Two":[26],"feedforward":[27],"NNs":[28],"(two":[29],"layers)":[30],"operate":[31],"on":[32],"input":[33],"features":[34],"extracted":[35],"from":[36],"frames":[38,52],"(10":[39],"ms":[40],"length)":[41],"DWT":[43],"and":[44,59,74,87],"statistical":[45],"measurement":[46],"in":[47,65],"order":[48],"classify":[50],"these":[51],"as":[53],"transient,":[54],"voiced":[55,57,75],"vowel,":[56],"consonant":[58,61],"unvoiced":[60],"categories.":[62],"Hard":[63],"our":[66],"earlier":[67],"are":[69],"used":[70],"detect":[72],"silence":[73],"closure":[76],"intervals.":[77],"The":[78],"new":[79],"is":[81],"tested":[82],"with":[83,89],"TIMIT":[85],"database":[86],"compared":[88],"other":[90],"algorithms":[91],"demonstrate":[93],"its":[94],"superior":[95],"performance.":[96]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}