Non-extensive Statistics for Feature Normalization in Speech Recognition
نویسندگان
چکیده
Statistical speech recognition is based on extensive statistics in which the additive property holds. On the other hand, it is well known that many complex systems, such as speech patterns, do not always have the additive property, and thus, do not follow extensive statistics. A framework of non-extensive statistics, proposed by Tsallis, can well represent the nonadditive characteristics of complex systems. In this paper, we introduce this framework to speech recognition. As an example, we apply it to feature normalization for recognizing noisy speech and show its effectiveness.
منابع مشابه
Feature normalization based on non-extensive statistics for speech recognition
Most compensation methods to improve the robustness of speech recognition systems in noisy environments such as spectral subtraction, CMN, and MVN, rely on the fact that noise and speech spectra are independent. However, the use of limited window in signal processing may introduce a cross-term between them, which deteriorates the speech recognition accuracy. To tackle this problem, we introduce...
متن کاملImproving the performance of MFCC for Persian robust speech recognition
The Mel Frequency cepstral coefficients are the most widely used feature in speech recognition but they are very sensitive to noise. In this paper to achieve a satisfactorily performance in Automatic Speech Recognition (ASR) applications we introduce a noise robust new set of MFCC vector estimated through following steps. First, spectral mean normalization is a pre-processing which applies to t...
متن کاملThe dependence of feature vectors under adverse noise
The performance degradation of automatic speech recognition system due to acoustic mismatch in training and testing environment is a severe problem for practical use of speech recognizer [1]. In this paper, we explore the effects of noise on individual speech feature vector statistics, and several feature normalization methods are used to compensate environment influence on feature vectors. We ...
متن کاملA recursive feature vector normalization approach for robust speech recognition in noise
The acoustic mismatch between testing and training conditions is known to severely degrade the performance of speech recognition systems. Segmental feature vector normalization [8] was found to improve the noise robustness of MFCC feature vectors and to outperform other state-of-the-art noise compensation techniques in speaker-dependent recognition. The objective of feature vector normalization...
متن کامل組合式倒頻譜統計正規化法於強健性語音辨識之研究 (Associative Cepstral Statistics Normalization Techniques for Robust Speech Recognition) [In Chinese]
The noise robustness property for an automatic speech recognition system is one of the most important factors to determine its recognition accuracy under a noise-corrupted environment. Among the various approaches, normalizing the statistical quantities of speech features is a very promising direction to create more noise-robust features. The related feature normalization approaches include cep...
متن کامل