Audio Synthesis
Audio synthesis aims to generate realistic sounds from various inputs, such as text, images, or other audio signals, primarily focusing on improving audio quality, efficiency, and controllability. Current research heavily utilizes diffusion models, often coupled with differentiable digital signal processing (DDSP) or generative adversarial networks (GANs), to achieve high-fidelity audio generation across diverse domains like speech, music, and sound effects. These advancements have significant implications for various fields, including virtual and augmented reality, assistive technologies, and creative media production, by enabling more realistic and expressive audio experiences.
Papers
November 22, 2024
September 4, 2024
July 30, 2024
July 19, 2024
July 15, 2024
July 5, 2024
June 27, 2024
June 26, 2024
June 25, 2024
June 13, 2024
June 11, 2024
June 7, 2024
June 1, 2024
April 20, 2024
March 28, 2024
March 26, 2024
February 9, 2024