登入選單
返回Google圖書搜尋
Hierarchical Neural Network Structures for Phoneme Recognition
Daniel VasquezRainer GruhnWolfgang Minker
出版Springer Science & Business Media, 2012-10-18
主題Technology & Engineering / Electronics / GeneralComputers / User InterfacesComputers / Intelligence (AI) & SemanticsComputers / Natural Language ProcessingTechnology & Engineering / Imaging SystemsTechnology & Engineering / Electrical
ISBN36423442409783642344244
URLhttp://books.google.com.hk/books?id=IRiaUn0K8lcC&hl=&source=gbs_api
EBookSAMPLE
註釋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.