← authors · overview

• High Fidelity Neural Audio Compression
  2022 · 280 citations
• Speech Resynthesis from Discrete Disentangled Self-Supervised Representations
  2021 · 206 citations
• Scaling Speech Technology to 1,000+ Languages
  2023 · 116 citations
• Simple and Controllable Music Generation
  2023 · 66 citations
• Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale
  2023 · 45 citations
• Textless Speech Emotion Conversion Using Discrete And Decomposed Representations
  2021 · 26 citations
• Voice Separation with an Unknown Number of Multiple Speakers
  2020 · 19 citations
• Text-Free Prosody-Aware Generative Spoken Language Modeling
  2021 · 16 citations
• Direct speech-to-speech translation with discrete units
  2021 · 7 citations
• Textually Pretrained Speech Language Models
  2023 · 7 citations
• fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit
  2021 · 4 citations
• ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement
  2022 · 4 citations
• Generative Spoken Dialogue Language Modeling
  2022 · 3 citations
• From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion
  2023 · 3 citations
• Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation
  2022 · 2 citations