6 papers · 1 filter
MambaVoiceCloning: Efficient and Expressive Text-to-Speech via State-Space Modeling and Diffusion Control
Sahil Kumar, Namrataben Patel, Honggang Wang +1
MambaVoiceCloning (MVC) asks whether the conditioning path of diffusion-based TTS can be made fully SSM-only at inference, removing all attention and explicit RNN-style recurrence…
Vision Transformer Segmentation for Visual Bird Sound Denoising
Sahil Kumar, Jialu Li, Youshan Zhang
Audio denoising, especially in the context of bird sounds, remains a challenging task due to persistent residual noise. Traditional and deep learning methods often struggle with ar…
Complex Image-Generative Diffusion Transformer for Audio Denoising
Junhui Li, Pu Wang, Jialu Li +1
The audio denoising technique has captured widespread attention in the deep neural network field. Recently, the audio denoising problem has been converted into an image generation…
Diffusion Gaussian Mixture Audio Denoise
Pu Wang, Junhui Li, Jialu Li +2
Recent diffusion models have achieved promising performances in audio-denoising tasks. The unique property of the reverse process could recover clean signals. However, the distribu…
DCHT: Deep Complex Hybrid Transformer for Speech Enhancement
Jialu Li, Junhui Li, Pu Wang +1
Most of the current deep learning-based approaches for speech enhancement only operate in the spectrogram or waveform domain. Although a cross-domain transformer combining waveform…
DPATD: Dual-Phase Audio Transformer for Denoising
Junhui Li, Pu Wang, Jialu Li +2
Recent high-performance transformer-based speech enhancement models demonstrate that time domain methods could achieve similar performance as time-frequency domain methods. However…