Significant progress has been made in symbolic music generation with the help of deep
learning techniques. However, the tasks covered by symbolic music generation have not …

The utilization of deep learning techniques in generating various contents (such as image,
text, etc.) has become a trend. Especially music, the topic of this paper, has attracted …

We tackle the task of conditional music generation. We introduce MusicGen, a single
Language Model (LM) that operates over several streams of compressed discrete music …

Expanding the language coverage of speech technology has the potential to improve
access to information for many more people. However, current speech technology is …

Large-scale generative models such as GPT and DALL-E have revolutionized the research
community. These models not only generate high fidelity outputs, but are also generalists …

YourTTS brings the power of a multilingual approach to the task of zero-shot multi-speaker
TTS. Our method builds upon the VITS model and adds several novel modifications for zero …

The ICASSP 2023 Deep Noise Suppression (DNS) Challenge marks the fifth edition of the
DNS challenge series. DNS challenges were organized from 2019 to 2023 to foster …

In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional
and unconditional waveform generation. The model is non-autoregressive, and converts the …

Speech language models (SpeechLMs) process and generate acoustic data only, without
textual supervision. In this work, we propose TWIST, a method for training SpeechLMs using …

We present a causal speech enhancement model working on the raw waveform that runs in
real-time on a laptop CPU. The proposed model is based on an encoder-decoder …