The use of speech recognition [2] [3] techniques in many practical applications has demonstrated the need for an Automatic speech Recognizer (ASR), it is a complex machine developed with the purpose to understand human speech. The conventional methods for speech recognition, such as HMM (Hidden Markov Model) and DTW (Dynamic Time Warping), are very complicated and time consuming. To apply Digital Signal Processor TMS320C6713 Digital signal processing Starter Kit (DSK) board is an attempt to implement a laboratory based Automatic speech Recognizer [1]. The proposed approach in this paper simplifies the algorithm using Linear Predictive Cepstral coefficients (LPCC) and Vector Quantization (VQ). The paper includes a performance evaluation of the above techniques on Matlab and application evaluation on DSK board. The database on which the training and testing was carried out is created in-house laboratory under calm and noise free environment. © 2012 Springer-Verlag GmbH.
CITATION STYLE
Shet, R. M., & Holambe, R. S. (2012). Automatic speech recognizer using digital signal processor. In Advances in Intelligent and Soft Computing (Vol. 167 AISC, pp. 599–607). https://doi.org/10.1007/978-3-642-30111-7_57
Mendeley helps you to discover research relevant for your work.