Voice intelligent classification method and system

A classification method and classification system technology, applied in speech analysis, speech recognition, instruments, etc., can solve problems such as slow convergence speed and poor classification effect, and achieve the effects of reducing parameters, speeding up convergence speed, and improving accuracy
CN109087635AInactive Publication Date: 2018-12-25HUBEI UNIV OF TECH
2 Cites 4 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
HUBEI UNIV OF TECH
Publication Date
2018-12-25
Estimated Expiration
Not applicable Β· inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

The invention discloses a voice intelligent classification method and system. The method includes: acquiring training set voice data; processing the training set voice data to obtain training set feature data; constructing an initialization model, wherein the initial classification model includes a first convolution layer, a first maximum pooling layer, a bidirectional cyclic neural network model,a second convolutional layer, a second maximum pooling layer, a first fully connected layer, a first dropout layer, a second fully connected layer, a second dropout layer, and a linear layer which are sequentially connected; training the initialization model by using the training set feature data to obtain a classification model; acquiring test set voice data; processing the test set voice data to obtain test set feature data; and classifying the test set feature data by using the classification mode. The method or system of the present invention can speed up the convergence speed in voice classification training, and can improve the judgment accuracy.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of speech classification, in particular to a speech intelligent classification method and system. Background technique

[0002] With the development of deep learning technology, speech classification technology based on deep learning is gradually being applied to various fields. Since speech data is a kind of time series data, and recurrent neural network is suitable for time series data processing, recurrent neural network is the core of speech classification. Speech classification is to extract features from given speech data, and use the extracted features as the input data of the cyclic neural network to train the neural network to achieve the effect of judging the category of the speech. It is often used in speech recognition, speech emotion analysis, etc. aspect. The design of the recurrent neural network structure used in speech classification often directly affects the effect of speech classification. When ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More