Robust voice recognition method based on acoustic model array

Abstract

The invention discloses a robust voice recognition method based on an acoustic model array. The robust voice recognition method comprises a training phase and a testing phase. At the training phase, a plurality of upper limiting frequencies are set for training voice according to the highest frequency of the voice, a plurality of groups of characteristic vectors are extracted and model training is performed to obtain the acoustic model array. At the testing phase, firstly, the upper limiting frequency of test voice is estimated according to a small quantity of self-adaptive voice in the testing environment; secondly, an acoustic model matched with the upper limiting frequency of the test voice is selected from the acoustic model array, and the parameters of the acoustic model are adjusted to obtain a testing environment acoustic model; finally, characteristic extraction is performed according to the upper limiting frequency of the test voice so as to obtain a characteristic vector of the noise-containing test voice, and acoustic decoding is performed on the characteristic vector by use of the testing environment acoustic model to obtain an identification result. The robust voice recognition method based on the acoustic model array is capable of improving the performance of a voice recognition system in a noise environment and improving the robustness of the system.

Description

technical field [0001] The invention belongs to the technical field of speech recognition, and specifically relates to extracting multiple sets of feature vectors in different frequency ranges according to a plurality of speech upper limit frequencies, constructing an array of acoustic models, and compensating the acoustic model matched with the upper limit frequency of the test speech to improve speech recognition. A model adaptation method for identifying system robustness. Background technique [0002] In the practical application of the speech recognition system, due to the influence of speech variability such as environmental noise, the pre-trained acoustic model often does not match the feature parameters extracted in the test environment, which will lead to a serious decline in the performance of the speech recognition system. Therefore, it is necessary to compensate the environment mismatch to improve the recognition performance of the speech recognition system. [...

AI Technical Summary

Problems solved by technology

However, the energy of the high-frequency part of the speech spectrum is small, and it is easily covered by noise in a noisy environment. Therefore, in a noisy test environment, the high-frequency part of the noisy speech spectrum is noise components, which not only cannot provide effective effects for speech recognition , and will adversely affect the model adaptation of the backend

Images