Explore MATLAB source code curated for "语音增强" with clean implementations, documentation, and examples.
The PESQ (Perceptual Evaluation of Speech Quality) metric evaluates speech quality using a MATLAB-compatible function syntax: [pesq_mos] = pesq('cleanfile.wav', 'enhanced.wav'). This function compares reference and processed audio files to generate a MOS-like score on a 1-5 scale (PESQ-MOS), where higher values indicate better perceptual quality. The implementation follows ITU-T P.862 standards for objective speech assessment.
This MATLAB toolbox for speech recognition and speech enhancement serves as an excellent reference implementation, featuring key algorithms like spectral subtraction, Wiener filtering, and deep learning-based enhancement techniques with practical code examples.
Speech Enhancement Results Evaluation Framework featuring four speech quality assessment methods: Signal-to-Noise Ratio (SNR), Segmental SNR (segSNR), Log Spectral Distance (LSD), and Perceptual Evaluation of Speech Quality (PESQ). Includes MATLAB implementation files for generating speech files with specified SNR levels. Also applicable to speech quality evaluation in other domains.