Multiple self-adaption based model compensation type speech recognition method

Abstract

The invention discloses a multiple self-adaption based model compensation type speech recognition method. The method includes firstly, subjecting parameters of a clean speech acoustic model trained in a training environment in advance to transformation so as to obtain a noisy speech acoustic model matched with a practical testing environment; then, taking the noisy speech acoustic model obtained through first self-adaption as a base environment acoustic model, constructing a transformation relation between noisy speech corresponding to the base environment acoustic model and noisy testing speech of a practical environment, and subjecting the base environment acoustic model to model self-adaption again, wherein the model self-adaption includes positive self-adaption and negative self-adaption; finally, comparing output likelihood values of the positive self-adaption and the negative self-adaption, and taking the noisy speech acoustic model with the larger likelihood value as a model self-adaption result. According to the multiple self-adaption based model compensation type speech recognition method, model self-adaption precision can be further improved so as to obtain the noisy speech acoustic model better matched with the practical testing environment.

Description

technical field [0001] The invention relates to a multi-adaptive model-compensated speech recognition method, which uses vector Taylor series to approximate the nonlinear environment transformation relationship between the base environment and the target environment, and updates the The mean value and variance of the acoustic model, the result of each adaptation is used as the basic environmental acoustic model, and the model is adapted again, and the multi-model adaptive method that approximates the nonlinear environmental transformation relationship through multiple model adaptations; belongs to the field of speech recognition technology . Background technique [0002] In practical applications, additive background noise is an important factor that causes the mismatch between the test environment and the training environment, and environmental noise is usually unavoidable. A speech recognition system with high accuracy in a quiet laboratory environment can recognize Perfo...

AI Technical Summary

Problems solved by technology

In harsh application environments such as low signal-to-noise ratio, due to the large difference between the pure training environment and the noisy test environment, it is difficult for the linear Taylor series expansion to approach the actual nonlinear transformation relationship well, so the model adaptation is obtained There is a large difference between the acoustic model of the noisy speech and the ideal acoustic model directly trained with a large number of noisy test speech

Images