Vocal print feature recognition method and system

Abstract

The embodiment of the invention provides a vocal print feature recognition method and a vocal print feature recognition system. The method comprises the following specific steps: after speech separation treatment based on hearing characteristics on pretreated noise-containing mixed noise, extracting a frequency cepstrum coefficient and a perceptual linear prediction coefficient of a signal, by utilizing the background distinction degree of the noise, analyzing the frequency cepstrum coefficient and the perceptual linear prediction coefficient under different noise environments so that the feature fusion is completed, and finally, in a pre-established vocal print feature template library, carrying out mode matching on the features after fusion by adopting a gaussian mixture model-universal background model (GMM-UBM). According to the vocal print feature recognition method, the human auditory system features and the traditional vocal print recognition method are combined, the problem that the vocal print recognition ratio under noise is low is solved from the point of bionics, and the vocal print feature recognition accuracy and system robustness under the noise environment are effectively promoted.

Description

technical field [0001] The present invention relates to the technical field of voice recognition, in particular to a voiceprint feature recognition method and system. Background technique [0002] As early as the 1930s, research on voiceprint recognition had been carried out among information researchers. In the early research, the Aural experiment and the feasibility verification of listening recognition were the key points in the field of voiceprint recognition. With the breakthrough of computer technology in hardware and algorithms, research on voiceprint recognition is no longer limited to a single human ear. Bell Laboratory of the United States has been in the leading position in the field of speech recognition for a long time. Laboratory member L G. Kesta completed the recognition through the analysis of the speech spectrogram, and he first proposed the concept of "voiceprint recognition". With the continuous exploration and innovation of scientific researchers in th...

AI Technical Summary

Problems solved by technology

However, the recognition accuracy of the existing voiceprint feature recognition methods in the noise environment is generally low, the system robustness is poor, and the application effect is not good.

Images