Picture for Sudhanshu Srivastava

Sudhanshu Srivastava

University of California, Santa Barbara

Fast and small footprint Hybrid HMM-HiFiGAN based system for speech synthesis in Indian languages

Feb 13, 2023
Figure 1 for Fast and small footprint Hybrid HMM-HiFiGAN based system for speech synthesis in Indian languages
Figure 2 for Fast and small footprint Hybrid HMM-HiFiGAN based system for speech synthesis in Indian languages
Figure 3 for Fast and small footprint Hybrid HMM-HiFiGAN based system for speech synthesis in Indian languages
Figure 4 for Fast and small footprint Hybrid HMM-HiFiGAN based system for speech synthesis in Indian languages
Viaarxiv icon

Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages

Nov 01, 2022
Figure 1 for Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages
Figure 2 for Technology Pipeline for Large Scale Cross-Lingual Dubbing of Lecture Videos into Multiple Indian Languages
Viaarxiv icon

Deep Learning--Based Scene Simplification for Bionic Vision

Jan 30, 2021
Figure 1 for Deep Learning--Based Scene Simplification for Bionic Vision
Figure 2 for Deep Learning--Based Scene Simplification for Bionic Vision
Figure 3 for Deep Learning--Based Scene Simplification for Bionic Vision
Figure 4 for Deep Learning--Based Scene Simplification for Bionic Vision
Viaarxiv icon

Deep Cross-Modal Audio-Visual Generation

Apr 26, 2017
Figure 1 for Deep Cross-Modal Audio-Visual Generation
Figure 2 for Deep Cross-Modal Audio-Visual Generation
Figure 3 for Deep Cross-Modal Audio-Visual Generation
Figure 4 for Deep Cross-Modal Audio-Visual Generation
Viaarxiv icon