Real Time Speech Recognition Using DSK TMS320C6713
نویسنده
چکیده
Speech recognition is an important field of digital signal processing. Automatic Speaker Recognition (ASR) objective is to extract features, characterize and recognize speaker. Mel Frequency Cepstral Coefficients (MFCC) is most widely used feature vector for ASR. MFCC is used for designing a text dependent speaker identification system. In this paper the DSP processor TMS320C6713 with Code Composer Studio (CCS) has been used for real time speech recognition. For analyzing the performance of speech recognition, we have considered here four speaker’s 20 number of spoken words as numbers and commands of length 2 sec in time. MFCC algorithm calculates cepstral coefficients of Mel frequency scale. After feature extraction from recorded speech, each Euclidian Distance (ED) from all training vectors is calculated using Gaussian Mixture Model (GMM) as it give better recognition for the speaker features. The command/voice having minimum ED is applied as similarity criteria. Keywords— Mel Frequency Cepstral Coefficients (MFCC), DSP Starter Kit (DSK), Code Composer Studio (CCS), Gaussian Mixture Model (GMM), Euclidian Distance (ED)
منابع مشابه
TMS320C6713 DSK Implementation of G. 711 Coded VoIP Signal
The quality of speech signal over a VoIP system is degraded by various network layer problems which include jamming, jitter, packet loss. Different types of noises also degrade the quality of speech signal such as external noise and quantization noise. This paper improves the quality of VoIP speech signal affected by these noises and network layer problems. The quality of degraded VoIP speech s...
متن کاملSimulation and Real Time Implementation of Spectral Subtraction and Wavelet De-Noising Embedded Algorithms for Speech Enhancement
The purpose of speech enhancement techniques is to improve quality and intelligibility of speech without producing any artifact. It is required either for the human listener or as a pre-processor in other speech processing systems. These algorithms are designed to suppress additive background noise. The spectral subtraction and wavelet denoising algorithms are commonly used in practice for back...
متن کاملPractical Guidelines and Examples for the Users of the TMS320C6713 DSK
This paper describes how the correct endian mode of the TMS320C6713 DSK board can be identified. It also explains how the TMS320C6713 DSK board can be used in the little endian and in the big endian modes for assembly language programming in particular and for signal processing in general. Similarly, it discusses how crucially important it is for a user of the TMS320C6713 DSK board to identify ...
متن کاملA Real Time Singing Voice Removal System Using DSP and Multichannel Audio Interface
Separating technique for singing voice from music accompaniment is very useful in original sound type Karaoke instrument. We propose a real-time system to separate singing voice from music accompaniment for stereo recordings. Proposed algorithm consists of two stages. The first stage is a spectral change detector. The last stage is a selective vocal separation in frequency bins. Our system cons...
متن کامل