Speech recognition method based on domain-invariant feature

Abstract

The invention discloses a speech recognition method based on a domain-invariant feature, and the method applies a speech domain-invariant feature extraction model to an end-to-end speech recognition model. The feature extraction model used in the speech recognition method aims at the robustness problem, and by adding more types of speech data to train the speech feature extraction model, better parameters can be obtained and a better domain-invariant feature extraction model can be obtained. The speech recognition method based on the domain-invariant feature uses unlabeled pure speech data totrain the feature extraction model, uses a small number of speeches with text annotation to train an end-to-end acoustic model, and provides important technical support for improving the robustness ofthe end-to-end acoustic model. Compared with the prior art, the speech recognition method based on the domain-invariant feature has higher recognition accuracy in different noise environments, smaller task quantity of speech annotation tasks, and faster training and testing speed of the models.

Description

technical field [0001] The invention belongs to the field of speech recognition, and relates to a robust speech recognition method in real noise environments, specifically a speech recognition method based on domain invariant features, which can be quickly and conveniently extended to new noise environments. Background technique [0002] In recent years, the application of end-to-end speech recognition models based on deep learning and sequence-to-sequence computing frameworks has become increasingly widespread. However, in the process of actually using speech recognition models, it is inevitable to encounter a variety of noise environments. The recognition accuracy is greatly reduced. Noise robustness refers to the ability of a speech recognition model to maintain the original recognition accuracy in a noisy environment. [0003] At present, the common methods to improve the noise robustness of the speech recognition model are: (1) adding a feature enhancement model for sp...

AI Technical Summary

Problems solved by technology

[0006] There is currently no method for applying speech domain-invariant feature extraction models to end-to-end speech recognition models

Images