Additional Information
| Author(s) | Alexandru Căruntu, Gavril Toderean, Marieta Gâta |
|---|
Experimental Results on Isolated Speech Recognition System
Gavril Toderean ♦ Marieta Gâta ♦ Alexandru Căruntu
Abstract
carpathian_2005_21_127_136_abstractFull PDF
carpathian_2005_21_127_136In this paper we described the development of Romanian ANN speech recognition system, which uses artificial neural networks. The network, which is composed by a three layer (a Multilayer Perceptron), is trained by conventional Back-propagation algorithm. The ANN speech recognition system based on Mel Frequency Cepstral Coefficients was developed using Matlab toolkit. The system was tested on the 50 isolated word Romanian speech corpus and it was training on a 50 distinct isolated word recognition task. The word recognition accuracy obtained was about 76%.
Recently posted
-
Stability of new functional equations and partial multipliers in Banach *-algebras
-
Characterizations of amenable gyrogroups related to Tarski's Theorem
-
Two new extragradient methods for solving pseudomonotone the equilibrium problem in Hilbert spaces
-
On the error estimates for the sequence of successive approximations for cyclic \varphi–contractions in metric spaces
-
Hybrid CG-Like Algorithm for Nonlinear Equations and Image Restoration
-
New class of n-order fractional differential equations and solvability in the double sequence space m^2(\Delta_{v}^{u}, \phi,p)
-
Constructing DNA Codes using Double Cyclic Codes of Odd and Even Lengths over F2 + u F2
-
Consequences of the product rule in Stieltjes differentiability
-
On the existence and uniqueness of fixed points in Banach spaces using the Krasnoselskij iterative method
-
A quaternionic product of simple ratios