Audio is an essential part of our life, but creating it often requires expertise and is time-
consuming. Research communities have made great progress over the past year advancing …

Text-to-speech models trained on large-scale datasets have demonstrated impressive in-
context learning capabilities and naturalness. However, control of speaker identity and style …

TorchAudio is an open-source audio and speech processing library built for PyTorch. It aims
to accelerate the research and development of audio and speech technologies by providing …

Historically, most speech models in machine-learning have used the mel-spectrogram as a
speech representation. Recently, discrete audio tokens produced by neural audio codecs …

Speech quality estimation has recently undergone a paradigm shift from human-hearing
expert designs to machine-learning models. However, current models rely mainly on …

Prompting has become a practical method for utilizing pre-trained language models (LMs).
This approach offers several advantages. It allows an LM to adapt to new tasks with minimal …

Large language models (LLMs) have significantly advanced audio processing through
audio codecs that convert audio into discrete tokens, enabling the application of language …

This paper proposes a generative pretraining foundation model for high-quality speech
restoration tasks. By directly operating on complex-valued short-time Fourier transform …

In this work, we introduce VERSA, a unified and standardized evaluation toolkit designed for
various speech, audio, and music signals. The toolkit features a Pythonic interface with …

Speech enhancement systems are typically trained using pairs of clean and noisy speech. In
audio-visual speech enhancement (AVSE), there is not as much ground-truth clean data …