In recent years, speaker recognition technology can achieve more than 90% accuracy in quiet environment, but it is not accurate in noise environment. In order to solve the problem of speaker recognition in noisy environment, a speaker recognition method based on deep residual network and improved Power Normalized Cepstral Coefficients (PNCC) features is proposed in the study. The PNCC features extraction algorithm is improved to be suitable for PNCC features parameter extraction in noisy environment. In order to further improve the training effect of the model, the deep residual network is adopted in this study to train the model, which effectively improves the model accuracy. In the recognition stage, in order to effectively suppress the influence of noise, this study proposes a VMD algorithm based on wavelet threshold denoising to improve the accuracy of speaker recognition. The experimental results show that compared with MFCC and PNCC features parameter extraction methods, the improved PNCC features extraction method is more conducive to feature extraction of speech signal under noise environment. Compared with other speaker recognition methods, the proposed speaker recognition method based on deep residual network and improved PNCC features has higher recognition accuracy.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.