Deep neural networks (DNN) techniques have become pervasive in domains such as
natural language processing and computer vision. They have achieved great success in …

We present RemixIT, a simple yet effective self-supervised method for training speech
enhancement without the need of a single isolated in-domain speech nor a noise waveform …

Speech enhancement has recently achieved great success with various deep learning
methods. However, most conventional speech enhancement systems are trained with …

Diffusion-based generative speech enhancement (SE) has recently received attention, but
reverse diffusion remains time-consuming. One solution is to initialize the reverse diffusion …

We propose RemixIT, a simple and novel self-supervised training method for speech
enhancement. The proposed method is based on a continuously self-training scheme that …

This work presents self-supervised learning methods for monaural speaker-specific (ie,
personalized) speech enhancement models. While general-purpose models must broadly …

Video-to-speech synthesis is the task of reconstructing the speech signal from a silent video
of a speaker. Previous approaches train on data from almost exclusively audio-visual …

Speaker identification or recognition task aims to identify persons from their voices. This
paper introduces a new feature extraction approach for robust speaker recognition named …

In traditional speech denoising tasks, clean audio signals are often used as the training
target, but absolutely clean signals are collected from expensive recording equipment or in …

The western black-crested gibbon (Nomascus concolor) is a rare and endangered primate
that inhabits southern China and northern Vietnam, and has become a key conservation …