Small data speech acoustic modeling method in speech recognition

Abstract

The invention belongs to the technical field of signal processing in the electronic industry, and aims at solving a problem that the discrimination performance of an acoustic model of a target language with just a little mark data is low. In order to solve the above problem, the invention provides a small data speech acoustic modeling method in speech recognition, and the method comprises the steps: carrying out the adversarial training of the acoustic features of many languages through a language adversarial discriminator, so as to build a multi-language adversarial bottleneck network model;taking the acoustic features of a target language as the input of the multi-language adversarial bottleneck network model, so as to extract the bottleneck features which is irrelevant to the language;carrying out the fusion of the bottleneck features which is irrelevant to the language with the acoustic features of the target language, so as to obtain fusion features; carrying out the training through the fusion features, so as to build an acoustic model of the target language. The method effectively irons out the defects, caused by a condition that the bottleneck information comprises the information correlated with the language, of the unremarkable improvement of the recognition performance of the target language and even the negative migration phenomenon in the prior art, thereby improving the voice recognition precision of the target language.

Description

technical field [0001] The invention relates to the technical field of signal processing in the electronics industry, in particular to a small data speech acoustic modeling method in speech recognition. Background technique [0002] Voice interaction is the most natural way of human-computer interaction, and voice recognition is the most important technology in voice interaction. In recent years, with the in-depth application of deep learning technology in speech recognition, speech recognition technology has made major breakthroughs. [0003] As we all know, deep learning requires a large amount of labeled data. For Mandarin or English, these labeled data are easy to obtain. However, for dialects, it is difficult to obtain a large amount of labeled data, and only a small amount of labeled data can be collected. Therefore, for establishing an acoustic model of a target language (such as a dialect) with a small amount of labeled data, the effect of using conventional deep le...

AI Technical Summary

Problems solved by technology

[0007] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem of low recognition accuracy of the acoustic model of the existing target language, the present invention provides a small data speech acoustic modeling method in speech recognition, the acoustic modeling method includes :

Images