BriefGPT.xyz
Sep, 2023
从大型语言模型到端到端自动语音识别系统的多重表示迁移
Multiple Representation Transfer from Large Language Models to End-to-End ASR Systems
HTML
PDF
Takuma Udagawa, Masayuki Suzuki, Gakuto Kurata, Masayasu Muraoka, George Saon
TL;DR
通过多重表示的大型语言模型的转移，我们研究了一种将语言学知识整合到端到端自动语音识别系统中的有效技术，证明了这种方法是传输单一表示的有效替代方案。
Abstract
Transferring the knowledge of
large language models
(LLMs) is a promising technique to incorporate linguistic knowledge into
end-to-end automatic speech recognition
(ASR) systems. However, existing works only tra
→