2 papers
eess.AS2024
HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis
Yuto Nishimura, Takumi Hirose, Masanari Ohi +2
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…
cs.CL2024
ELP-Adapters: Parameter Efficient Adapter Tuning for Various Speech Processing Tasks
Nakamasa Inoue, Shinta Otake, Takumi Hirose +2
Self-supervised learning has emerged as a key approach for learning generic representations from speech data. Despite promising results in downstream tasks such as speech recogniti…