2022/10/28 by Shulin He, Wei Rao, He, Shulin +13
Computer Science · Health Professions · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Infant Health and Development #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2210.15853
openalex publication_date 2022/10/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Most neural network speech enhancement models ignore speech production mathematical models by directly mapping Fourier transform spectrums or waveforms. In this work, we propose a neural source filter network for speech enhancement. Specifically, we use homomorphic signal processing and cepstral analysis to obtain noisy speech's excitation and vocal tract. Unlike traditional signal processing, we use an attentive recurrent network (ARN) model predicted ratio mask to replace the liftering separation function. Then two convolutional attentive recurrent network (CARN) networks are used to predict the excitation and vocal tract of clean speech, respectively. The system's output is synthesized from the estimated excitation and vocal. Experiments prove that our proposed method performs better, with SI-SNR improving by 1.363dB compared to FullSubNet.