Speech-emotion recognition system based on improved Fukunage-koontz transformation

Abstract

The invention discloses a speech-emotion recognition method based on improved Fukunage-koontz transformation (FKT). Transformation by utilizing the method can effectively realize feature dimension reduction. During dimension reduction, in consideration of the internal manifold structure of speech, a parameter tau capable of describing inter-frame relevance is introduced, and weighting is performed when feature covariance is calculated so as to find the feature with maximum / minimum variance after dimension reduction. In addition, by taking the variance as the discrimination information of classification, the recognition of various speech emotions is realized by adopting a k nearest neighbor recognition method. Compared with the prior similar recognition method, the method can effectively improve recognition rate.

Description

technical field [0001] The invention relates to a speech recognition method, in particular to a speech emotion recognition system and method. Background technique [0002] The speech emotion automatic recognition technology mainly includes two problems: one is to use the features in the speech signal as emotion recognition, that is, the problem of emotional feature extraction, including feature extraction and selection; the other is how to classify specific speech data, That is, the problem of pattern recognition, including various pattern recognition algorithms, such as nearest neighbors, neural networks, support vector bases, etc. [0003] The emotional feature parameters commonly used in speech emotion recognition include: linear predictive coefficient (LPC), linear predictive cepstral coefficient (LPCC), Mel cepstral coefficient (MFCC), short-term energy, fundamental frequency, formant, etc. Among them, LPC can be considered as an estimation of the all-pole model of the...

AI Technical Summary

Problems solved by technology

At present, the commonly used speech features are mainly extracted in units of frames, and then the global statistical features are obtained, which cannot effectively represent the structural characteristics of speech frames. PCA and LDA are used to reduce dimensionality and are mostly based on global considerations, which cannot effectively reflect the internal structure of speech.

Traditional FKT is a global-based dimensionality reduction method, which cannot consider the correlation characteristics between sample values ​​in local time, and cannot effectively reflect the manifold structure inside the sample.

Images