Voice conversion (VC) can be achieved by first extracting source content information and
target speaker information, and then reconstructing waveform with these information …

Transfer learning has proven to be crucial in advancing the state of speech and natural
language processing research in recent years. In speech, a model pre-trained by self …

The foundation model paradigm leverages a shared foundation model to achieve state-of-
the-art (SOTA) performance for various tasks, requiring minimal downstream-specific data …

Deep generative models can generate high-fidelity audio conditioned on varioustypes of
representations (eg, mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)) …

Self-supervised speech representation learning (speech SSL) has demonstrated the benefit
of scale in learning rich representations for Automatic Speech Recognition (ASR) with …

Diffusion-based generative models have recently exhibited powerful generative
performance. However, as many attributes exist in the data distribution and owing to several …

Neural text-to-speech (TTS) has achieved human-like synthetic speech for single-speaker,
single-language synthesis. Multilingual TTS systems are limited to resource-rich languages …

Self-supervised learning (SSL) based speech foundation models have been applied to a
wide range of ASR tasks. However, their application to dysarthric and elderly speech via …

Foundation models (FMs), that are trained on broad data at scale and are adaptable to a
wide range of downstream tasks, have brought large interest in the research community …

In this work, we propose a zero-shot voice conversion method using speech representations
trained with self-supervised learning. First, we develop a multi-task model to decompose a …