Deep learning-based unusual speech distinguishing method

Abstract

The invention discloses a deep learning-based unusual speech distinguishing method. The method comprises the following steps: input speech is acquired, resampling, pre-emphasis and framing and windowing preprocessing are carried out on the input speech, and preprocessed speech is obtained; a mel-frequency cepstral coefficient (MFCC) characteristic vector is extracted for the preprocessed speech; the speech segments with different frames are regularized to a fixed number of frames, and each speech segment obtains a corresponding mel-frequency cepstral coefficient characteristic vector; a convolutional depth confidence network is built; the mel-frequency cepstral coefficient characteristic vectors are inputted to the convolutional depth confidence network for training, and the states of input speech are classified; and according to a classification result, a hidden Markov model is called for template matching and a speech recognition result is obtained. Multiple nonlinear transform layers of the convolutional depth confidence network are used, the inputted MFCC characteristics are mapped to higher-dimensional space, the hidden Markov model is then used to carry out modeling on different states of speech, and the speech recognition accuracy is improved.

Description

technical field [0001] The invention relates to the field of intelligent speech processing research, in particular to a method for distinguishing abnormal speech based on deep learning. Background technique [0002] Speech is one of the important ways for humans and machines to interact. After decades of research, speech recognition technology has been greatly developed and has penetrated into our daily life. However, the existing research on speech recognition has the following problems: [0003] In real life, the speaker's abnormal health or other reasons will cause the input speech to shift from normal speech to abnormal speech, and will bring more noise interference. Abnormal speech generally refers to speech with complex background noise, speech with intentional changes in speaking methods or habits, speech with developmental organ lesions, etc. [0004] Another problem is that traditional speech recognition systems often use linear predictive cepstral coefficients and...

AI Technical Summary

Problems solved by technology

[0004] Another problem is that traditional speech recognition systems often use linear predictive cepstral coefficients and Mel-frequency cepstral coefficients. The main information in these underlying acoustic features is the pronunciation of text features, and speaker information is easily affected by this information, channel and noise. Information interference, which reduces the recognition performance of the system

Images