SEANet: A Multi-modal Speech Enhancement Network
Learning to Denoise Historic Music
Real-time Speech Frequency Bandwidth Extension
MicAugment: One-shot Microphone Style Transfer
One-shot conditional audio filtering of arbitrary sounds
CycleGAN-Based Unpaired Speech Dereverberation
Text Driven Separation of Arbitrary Sounds
BASNet: Binaural Angular Separation Network
SoundStream: An End-to-End Neural Audio Codec
Disentangling speech from surroundings in a neural audio codec
StreamVC: Real-Time Low-Latency Voice Conversion
AudioLM: A Language Modeling Approach to Audio Generation
MusicLM: Generating Music From Text
SpeechPainter: Text-conditioned Speech Inpainting
AudioPaLM: A Large Language Model That Can Speak and Listen
SoundStorm: Efficient Parallel Audio Generation
Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision