2025
HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis
ICLR 2025poster
Recently, Text-to-speech (TTS) models based on large language models (LLMs) that translate natural language text into sequences of discrete audio tokens have gained great research attention, with advances in neural audio codec (NAC) mod- els using residual vector quantization (RVQ). However, long-fo…