Xu Tan

This paper presents a method to enhance language models' interaction with tools.

bGPT focuses on binary data for better digital modeling and predictions.

RALL-E enhances text-to-speech synthesis for clearer, more natural speech.

MuPT utilizes ABC notation for effective music generation with AI.

FlashSpeech offers rapid, high-quality speech synthesis solutions.

A new method helps balance training data for better AI performance.

A new method to create music that fits video content effectively.

X-Codec improves audio generation by integrating semantic understanding into processing.

BigCodec improves sound quality in low-bitrate audio transmission.

A look at the Codec-SUPERB challenge results and codec performance metrics.