A TMS320C40 based Speech Recognition System for Embedded Applications
نویسندگان
چکیده
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
منابع مشابه
Classification of emotional speech using spectral pattern features
Speech Emotion Recognition (SER) is a new and challenging research area with a wide range of applications in man-machine interactions. The aim of a SER system is to recognize human emotion by analyzing the acoustics of speech sound. In this study, we propose Spectral Pattern features (SPs) and Harmonic Energy features (HEs) for emotion recognition. These features extracted from the spectrogram ...
متن کاملبهبود عملکرد سیستم بازشناسی گفتار پیوسته بوسیله ویژگیهای استخراج شده از مانیفولدهای گفتاری در فضای بازسازی شده فاز
The design for new feature extraction methods out of the speech signal and combination of their obtained information is one of the most effective approaches to improve the performance of automatic speech recognition (ASR) system. Recent researches have been shown that the speech signal contains nonlinear and chaotic properties, but the effects of these properties are not used in the continuous ...
متن کاملHigh Performance Qualitative Simulation on aMulti { DSP Architecture
We present a special-purpose computer architecture for the qualitative simulator QSim, which is mainly used in artiicial intelligence (AI) applications. This architecture consists of DSPs TMS320C40 and specialized coprocessors (Xilinx FPGAs). We stress the distinct algorithm characteristic of qualitative simulation compared to DSP applications. We also demonstrate the suitability of the DSP TMS...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeech Emotion Recognition Based on Power Normalized Cepstral Coefficients in Noisy Conditions
Automatic recognition of speech emotional states in noisy conditions has become an important research topic in the emotional speech recognition area, in recent years. This paper considers the recognition of emotional states via speech in real environments. For this task, we employ the power normalized cepstral coefficients (PNCC) in a speech emotion recognition system. We investigate its perfor...
متن کامل