LEADER 00956nam0-22003251i-450- 001 990004457440403321 005 20130903102627.0 035 $a000445744 035 $aFED01000445744 035 $a(Aleph)000445744FED01 035 $a000445744 100 $a19990604e19341839km-y0itay50------ba 101 0 $ager 102 $aAT 105 $aa-------00--- 200 1 $aDeutsche Geschichte im Zeitalter der Reformation$fLeopold von Ranke 205 $aUngekürzte Textausgabe 210 $aWien$cIm Phaidon Verlag$d[1934] 215 $a1287 p.$cill.$d22 cm 517 1 $aGeschichte der Reformation 610 0 $aGermania - 1517-1648 676 $a943.03 700 1$aRanke,$bLeopold von$f<1795-1886>$0386293 801 0$aIT$bUNINA$gRICA$2UNIMARC 901 $aBK 912 $a990004457440403321 952 $a943 RAN 1$bBibl. 12372$fFLFBC 959 $aFLFBC 996 $aDeutsche Geschichte im Zeitalter der Reformation$9544069 997 $aUNINA LEADER 03065nam 2200661 a 450 001 9910437904803321 005 20200520144314.0 010 $a9783642344251 010 $a3642344259 024 7 $a10.1007/978-3-642-34425-1 035 $a(CKB)2670000000279603 035 $a(EBL)1082805 035 $a(OCoLC)819070494 035 $a(SSID)ssj0000798734 035 $a(PQKBManifestationID)11440637 035 $a(PQKBTitleCode)TC0000798734 035 $a(PQKBWorkID)10759652 035 $a(PQKB)10527509 035 $a(DE-He213)978-3-642-34425-1 035 $a(MiAaPQ)EBC1082805 035 $z(PPN)258852801 035 $a(PPN)168326906 035 $a(EXLCZ)992670000000279603 100 $a20121108d2013 uy 0 101 0 $aeng 135 $aur|n|---||||| 181 $ctxt 182 $cc 183 $acr 200 10$aHierarchical neural network structures for phoneme recognition /$fDaniel Vasquez, Rainer Gruhn, and Wolfgang Minker 205 $a1st ed. 2013. 210 $aHeidelberg $cSpringer$d2013 215 $a1 online resource (145 p.) 225 0$aSignals and communication technology,$x1860-4862 300 $aDescription based upon print version of record. 311 08$a9783642432101 311 08$a3642432107 311 08$a9783642344244 311 08$a3642344240 320 $aIncludes bibliographical references and index. 327 $aBackground 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. 330 $aIn this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are evaluated on the phoneme recognition task where a  Hybrid Hidden Markov Model/Artificial Neural Network paradigm is used. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron. Additionally, the output of the first level serves as a second level input. The computational speed of the phoneme recognizer can be substantially increased by removing redundant information still contained at the first level output. Several techniques based on temporal and phonetic criteria have been investigated to remove this redundant information. The computational time could be reduced by 57% whilst keeping the system accuracy comparable to the baseline hierarchical approach. 410 0$aSignals and Communication Technology,$x1860-4862 606 $aPhonemics 606 $aWord recognition 615 0$aPhonemics. 615 0$aWord recognition. 676 $a414 700 $aVasquez C$b Daniel$01758198 701 $aGruhn$b Rainer$01758199 701 $aMinker$b Wolfgang$0935692 801 0$bMiAaPQ 801 1$bMiAaPQ 801 2$bMiAaPQ 906 $aBOOK 912 $a9910437904803321 996 $aHierarchical neural network structures for phoneme recognition$94196357 997 $aUNINA