Self-adapting method of DNN acoustic model based on personal identity characteristics

Abstract

The invention discloses a self-adapting method of a DNN acoustic model based on personal identity characteristics. The method solves the problems of easy over-fitting, poor personal identity representation capability and low robustness in the self-adapting training. The method comprises the following steps of: extracting personal identity characteristics, and inputting the MFCC characteristics asthe DNN model of a non-specific speaker; establishing a GMM-HMM speech recognition system; building a DNN-HMM baseline system of the DNN acoustic model with a plurality of hidden layers; and carryingout self-adapting training on the individual identity characteristics of the DNN acoustic model layer by layer to obtain the DNN acoustic model which has self-adapting capability to a specific speaker. In personal identity characteristic extraction, a weight matrix decomposition of the last hidden layer of DNN model is replaced by VAD technology. According to the method, a small amount of speakerdata is fully utilized to adjust the model parameters so that the recognition accuracy rate of the specific speaker is improved. And the complexity is low, and the recognition performance is obviouslyimproved. The method is used for intelligent systems related to speech recognition or communications, medical treatment, vehicle mounting and the like.

Description

technical field [0001] The invention belongs to the field of communication technology, and mainly relates to the speaker feature extraction technology of personal identity i-vector, in particular to an adaptive method of DNN acoustic model based on personal identity (i-vector) feature, which is used for non-specific speaker voice identify. Background technique [0002] In recent years, the deep neural network DNN has achieved great success in speech recognition. In speech acoustic modeling, the HMM-DNN system based on the invisible Markov-deep neural network is compared with the traditional invisible Markov-Gaussian The hybrid model HMM-GMM system has better acoustic discrimination and greatly improves the performance of speech recognition. DNN has become the mainstream acoustic model. [0003] However, there is still a problem in the above two systems that the speaker's voice of the training data does not match the target speaker's voice, that is, it is assumed that the tr...

AI Technical Summary

Problems solved by technology

[0003] However, the problem that still exists in the above two systems is that the speaker's voice of the training data does not match the target speaker's voice, that is, it is assumed that the training data and the test data obey the same distribution

This method overcomes the problem of frame classification accuracy decline, and the recognition performance has been improved to a certain extent, but the recognition is not good, because the improved i-vector is simply spliced ​​with the original input features at the input layer, and a small amount of speech cannot be fully utilized. Personal information, affecting system recognition performance

[0008] Some research institutions choose the bottleneck feature with stronger representation ability instead of MFCC feature to obtain personal identity i-vector. The bottleneck layer is introduced into the structure, which reduces the frame classification accuracy of DNN

[0009] To sum up, the current adaptive research methods have achieved great success, but due to the lack of full use of a small amount of adaptive data, and the complex network structure, high computational complexity, and insufficient stability

Images