Phonetic feature processing method of voiceprint identification in noise environment

Abstract

The invention provides a phonetic signal feature processing method of voiceprint identification in a noise environment, which includes the steps of: (1) carrying out early stage processing on signals according to a phonetic signal characteristic, the processing including signal pre-emphasis, endpoint detection, and selection of window functions; (2) estimating a fundamental tone period of a sounding individual, carrying out spectrum smoothing processing on the phonetic signal based on the fundamental tone period, obtaining a new spectrum envelope, calculating the energy passing through a Mel filter, and finally obtaining a Mel smoothing coefficient (SFCC) through Discrete Cosine Transform (DCT) calculation; and (3) carrying out post-processing on the SFCC by combination of a mean value reduction method, variance normalization, a time sequence filter method, and a weight autoregression moving average filter method, and obtaining a regression balance parameter (MVDA). The purpose is to remove individual sounding unstable factors by smoothing the spectrum envelope and to remove the ambient noise influence through a post-processing algorithm, and the false identification rate of the voiceprint identification is finally reduced.

Description

technical field [0001] The invention relates to the field of speech signal processing, and proposes a speech feature extraction method based on pitch characteristics and noise characteristics. Background technique [0002] With the development of speech science and information communication technology, as a more convenient identity verification technology, voiceprint recognition technology has made remarkable progress. As one of the most basic natural attributes of human beings, language is the most direct and convenient way for information transmission between human beings. As an individual, the vocal organs are not only related to innate factors, but also greatly affected by factors such as the acquired developmental environment, so the voice has a very significant individual color. This individual characteristic also gave rise to a scientific research hotspot - voiceprint recognition. When an individual is speaking, the voice produced is related to the individual's voca...

AI Technical Summary

Problems solved by technology

The acoustic model only uses the data in the voice sample library for training, and the voice collection is usually in a low-noise environment, which is often difficult to match with a variety of noise environments. The feature distortion caused by environmental noise reduces the robustness of voiceprint recognition. sex

Images