00728nam 2200265 450 991057920140332120220707102610.0978-3-487-08638-520220707d2021----u y0engy50 bageryf y 001yyDer BildungswortschatzDarstellung und WörterverzeichnisGerhard Augst7. AuflageHildesheimOlms2021219 p.21 cm430.14433.51Augst,Gerhard245981ITUNINAREICATUNIMARCBK9910579201403321430.14 AUGG 012022/781FLFBCFLFBCDer Bildungswortschatz2881885UNINA03065nam 2200661 a 450 991043790480332120200520144314.09783642344251364234425910.1007/978-3-642-34425-1(CKB)2670000000279603(EBL)1082805(OCoLC)819070494(SSID)ssj0000798734(PQKBManifestationID)11440637(PQKBTitleCode)TC0000798734(PQKBWorkID)10759652(PQKB)10527509(DE-He213)978-3-642-34425-1(MiAaPQ)EBC1082805(PPN)258852801(PPN)168326906(EXLCZ)99267000000027960320121108d2013 uy 0engur|n|---|||||txtccrHierarchical neural network structures for phoneme recognition /Daniel Vasquez, Rainer Gruhn, and Wolfgang Minker1st ed. 2013.Heidelberg Springer20131 online resource (145 p.)Signals and communication technology,1860-4862Description based upon print version of record.9783642432101 3642432107 9783642344244 3642344240 Includes bibliographical references and index.Background in Speech Recognition -- Phoneme Recognition Task -- Hierarchical Approach and Downsampling Schemes -- Extending the Hierarchical Scheme: Inter and Intra Phonetic Information -- Theoretical framework for phoneme recognition analysis.In this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are evaluated on the phoneme recognition task where a  Hybrid Hidden Markov Model/Artificial Neural Network paradigm is used. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron. Additionally, the output of the first level serves as a second level input. The computational speed of the phoneme recognizer can be substantially increased by removing redundant information still contained at the first level output. Several techniques based on temporal and phonetic criteria have been investigated to remove this redundant information. The computational time could be reduced by 57% whilst keeping the system accuracy comparable to the baseline hierarchical approach.Signals and Communication Technology,1860-4862PhonemicsWord recognitionPhonemics.Word recognition.414Vasquez C Daniel1758198Gruhn Rainer1758199Minker Wolfgang935692MiAaPQMiAaPQMiAaPQBOOK9910437904803321Hierarchical neural network structures for phoneme recognition4196357UNINA