Abstract
In the case of small signal-to-noise ratio, the performance of traditional speech endpoint detection algorithm drops rapidly, sometimes it even cannot work normally. Based on wavelet transform and multi-resolution analysis, this paper analyzes and studies the wavelet coefficient variance algorithm and sub band average energy algorithm in speech endpoint detection. It optimizes these two algorithms by using the frequency-domain difference between speech and noise. The scheme combines the advantages of PCA and RBF neural network to complement each other, and proposes a speech endpoint detection approach WaRBF. The simulation results show that WaRBF algorithm improves the accuracy of speech endpoint detection, which has better antinoise and robustness. The detection results are more stable and reliable, which shows better practical application value.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
