Hierarchical Neural Network Structures for Phoneme Recognition

Hierarchical Neural Network Structures for Phoneme Recognition

لا توجد تقييمات بعد
Nov 9, 2014 · الإنجليزية · غلاف ورقي (152 صفحات)
أضف إلى الرف

قيم هذا الكتاب


تصدير مجلة الكتاب

تفاصيل الكتاب

تنسيق غلاف ورقي
صفحات 152
لغة الإنجليزية
منشور Nov 9, 2014
الناشر Springer
رقم ISBN-10 3642432107
رقم ISBN-13 9783642432101

الوصف

In this book, hierarchical structures based on neural networks are investigated for automatic speech recognition. These structures are mainly evaluated within the phoneme recognition task under the Hybrid Hidden Markov Model/Artificial Neural Network (HMM/ANN) paradigm. The baseline hierarchical scheme consists of two levels each which is based on a Multilayered Perceptron (MLP). Additionally, the output of the first level is used as an input for the second level. This system can be substantially speeded up by removing the redundant information contained at the output of the first level.
أضف إلى الرف

قيم هذا الكتاب


تصدير مجلة الكتاب