A TMS320C40 based Speech Recognition System for Embedded Applications

TL;DRAbstract

: This paper describes a prototype implementation of a speech recognition system for embedded applications. The recognition system is comprised of a feature extractor and a classifier. The feature extractor is based on a 64-point Fast Fourier Transformation (FFT); the classifier is based on discrete-density Hidden Markov Models (HMM) with a variable codebook size. Training as well as classification are implemented using the Viterbi algorithm. The prototype is implemented on a digital signal processor (DSP) of type TMS320C40 from Texas Instruments. The recognition rate and the performance are experimentally evaluated using a test vocabulary of 20 words. keywords: automatic speech recognition, Hidden Markov Models, TMS320C40 1. INTRODUCTION Automatic speech recognition (ASR) has been a very active research area for a long time, and much progress has been achieved within the last years. Nowadays, many applications have been extended by ASR techniques to enable an easy and natural way of..

Chat with Paper

AI Agents for this Paper