Speech recognition method and device, equipment and medium

Abstract

The embodiment of the invention provides a voice recognition method and device, equipment and a medium. The method comprises the steps: converting acquired audio data into a corresponding spectrogram;judging whether the frame number of the spectrogram is a preset frame number or not; if the frame number of the spectrogram is not the preset frame number, carrying out zero filling on the spectrogram, so as to making the frame number of a spectrogram to be identified obtained after zero filling is the preset frame number; and inputting the spectrogram to be identified into a multi-task convolutional neural network acoustic model. The spectrogram is directly input into an acoustic model, and then the text of the audio data is recognized. Compared with the prior art for calculating the information loss on the frequency domain caused by MFCC characteristics, the method and device have the advantages that the loss of the input characteristics is reduced, the identification degree of the audio data is increased, and the extraction of the characteristic information by the acoustic model is facilitated.

Description

technical field [0001] The present invention relates to speech recognition technology and deep learning technology, in particular to a speech recognition method, device, equipment and medium. Background technique [0002] With the popularity of intelligent products, speech recognition technology as a human-computer interaction is becoming more and more important. [0003] In speech recognition, most of the traditional speech features are used for speech recognition at present. Among them, traditional speech features include: MFCC features, FBANK features and other artificially designed features, which cause information loss in the frequency domain, especially in the high-frequency region, resulting in low accuracy of speech recognition. At the same time, the traditional single-task network model can easily overfit on the training data, resulting in a decline in the recognition rate on the test set. Contents of the invention [0004] In view of the above problems, embodim...

AI Technical Summary

Problems solved by technology

Among them, traditional speech features include: MFCC features, FBANK features and other artificially designed features, which cause information loss in the frequency domain, especially in the high-frequency region, resulting in low accuracy of speech recognition

At the same time, the traditional single-task network model can easily overfit on the training data, resulting in a decline in the recognition rate on the test set.

Images