Abstract: Birds are essential indicators of ecological health, yet traditional identification methods rely heavily on expert knowledge and visual observation. This paper presents an AI-powered system ...

Abstract: In this work, we propose CleanMel, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (ASR) performance ...

This repository contains the implementation of (MQGAN) for audio synthesis. The project is structured to facilitate the entire workflow from data preparation to model deployment.

Diffusion Speech is a diffusion-based text-to-speech model. Our speech synthesis pipeline is quite simple. We use a diffusion transformer model (DiT) to predict the duration of each phoneme. Then we ...