Improved Speech Enhancement with the Wave-U-Net
We study the use of the Wave-U-Net architecture for speech enhancement, a model introduced by Stoller et al for the separation of music vocals and accompaniment. This end-to-end learning method for audio source separation operates directly in the time domain, permitting the integrated modelling of phase information and being able to take large temporal contexts into account. Our experiments show that the proposed method improves several metrics, namely PESQ, CSIG, CBAK, COVL and SSNR, over the state-of-the-art with respect to the speech enhancement task on the Voice Bank corpus (VCTK) dataset. We find that a reduced number of hidden layers is sufficient for speech enhancement in comparison to the original system designed for singing voice separation in music. We see this initial result as an encouraging signal to further explore speech enhancement in the time-domain, both as an end in itself and as a pre-processing step to speech recognition systems.
Code (3)
Tasks
Audio Source SeparationSpeech Enhancementspeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Improved Speech Enhancement with the Wave-U-Net
We study the use of the Wave-U-Net architecture for speech enhancement, a model introduced by Stoller et al for the separation of music vocals and accompaniment. This end-to-end learning method for audio source separati…
Audio Source SeparationSpeech Enhancementspeech-recognitionSpeech RecognitionSingle Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks
In recent decades, neural network based methods have significantly improved the performace of speech enhancement. Most of them estimate time-frequency (T-F) representation of target speech directly or indirectly, then re…
Speech EnhancementiSEGAN: Improved Speech Enhancement Generative Adversarial Networks
Popular neural network-based speech enhancement systems operate on the magnitude spectrogram and ignore the phase mismatch between the noisy and clean speech signals. Conditional generative adversarial networks (cGANs) s…
Speech EnhancementImproving multichannel speech enhancement through accurate room-acoustic simulations
Room-acoustic simulations are widely used to augment training data for deep-learning-based speech enhancement. While most pipelines rely on simplified geometrical acoustics, wave-based approaches offer greater physical a…
Speech EnhancementA Study on Speech Enhancement Based on Diffusion Probabilistic Model
Diffusion probabilistic models have demonstrated an outstanding capability to model natural images and raw audio waveforms through a paired diffusion and reverse processes. The unique property of the reverse process (nam…
Speech Enhancement