Objective: The objective of this review article is to give a complete review of various techniques that are used for speech recognition purposes over two decades. Methods: VAD-Voice Activity Detection, SAD-Speech Activity Detection techniques are discussed that are used to distinguish voiced from unvoiced signals and MFCC- Mel Frequency Cepstral Coefficient technique is discussed which detects specific features. Results: The review results show that research in MFCC has been dominant in signal processing in comparison to VAD and other existing techniques. Conclusion: A comparison of different speaker recognition techniques that were used previously were discussed and those in current research were also discussed and a clear idea of the better technique was identified through the review of multiple literature for over two decades. Keywords: Cepstral analysis, Mel-frequency cepstral coefficients, signal processing, speaker recognition, voice activity detection.
展开▼