The Relationship Between the Missing Rate of User-Spoken Sentences and the Appropriateness of LLM-Generated Replies

Abstract

This research focuses on making spoken dialogue systems faster when using large language models (LLMs). In a verbal dialogue system, the response using LLMs can only generate after the whole text of the user's speech is recognized. This causes a delay before the system replies. To solve this problem, we propose a method that starts generating a response while the user is still speaking, without waiting for them to finish. However, this means that the system has to respond to sentences that might be incomplete, which could affect the content of the response. In this study, we analyze how the response quality changes depending on how much of the user's sentence is missing.