- Inicio
- Listar por autor
Listar por autor "Gao, Jiechao"
Mostrando ítems 1-2 de 2
-
E2E-V2SResNet: Deep residual convolutional neural networks for end-to-end video driven speech synthesis
Saleem, Nasir; Gao, Jiechao; Irfan, Muhammad; Verdú, Elena ; Parra Puente, Javier (Image and vision computing, 2022)Speechreading which infers spoken message from a visually detected articulated facial trend is a challenging task. In this paper, we propose an end-to-end ResNet (E2E-ResNet) model for synthesizing speech signals from the ... -
Regularized sparse features for noisy speech enhancement using deep neural networks
Khattak, Muhammad Irfan; Saleem, Nasir; Gao, Jiechao; Verdú, Elena ; Parra Fuente, Javier (Computers and Electrical Engineering, 2022)A speech enhancement algorithm improves the perceptual aspects of a speech degraded by noise signals. We propose a phase-aware deep neural network (DNN) using the regularized sparse features for speech enhancement. A ...