Speech classification method based on deep neural network

Abstract

The invention discloses a speech classification method based on a deep neural network, and aims at solving different speech classification problems through a unified algorithm model. The method of theinvention includes the steps of S1, converting a speech into a corresponding spectrogram; segmenting the complete spectrogram along the frequency domain into blocks to obtain a local frequency domaininformation set; S2, taking the complete and local frequency domain information as inputs of a model respectively, and based on the different inputs, the convolutional neural network being capable ofextracting local and global features; S3, using an attention mechanism to fuse global and local feature expressions to form a final feature expression; S4, using tagged data to train the network by gradient descent and back propagation algorithms; and S5, using the trained parameters for an untagged speech and taking the classification of highest probability that the model outputs as a predictionresult. The method of the invention realizes a unified algorithm model for different speech classification problems, and improves the accuracy on multiple speech classification problems.

Description

technical field [0001] A speech classification method based on a deep neural network is used to process different speech classification tasks, involving speech signal processing, artificial intelligence and other technical fields. Background technique [0002] With the rapid development of computer technology, human beings are increasingly dependent and demanding on computers, how to better interact with computers has become a research hotspot. As the most common and natural way of communication in daily life, speech contains a huge amount of information, such as the speaker's accent, the speaker's emotional state, and so on. The computer's speech classification and recognition ability is an important part of the computer's speech processing and the key premise for realizing the natural human-computer interaction interface, which has great research value and application value. Speech classification technology is a very important research direction, it plays an important rol...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a speech classification method based on a deep neural network in view of the above deficiencies, and solves the problems in the prior art that are only aimed at unique single-task classification or data feature extraction methods, and high-dimensional data are difficult to handle.

Images