生成モデルによる応答タイミング推定と動的Prompt-Tuneを用いた応答詳細性のパラメーター制御

書誌事項

タイトル別名
  • Estimation of Response Timing by Generative Model and Parameter Control of Response Substantialness Using Dynamic-Prompt-Tune

抄録

<p>A spoken dialogue system is required to continuously listen to a human user for smooth conversation. We propose a method that simultaneously performs response generation and response timing estimation. Our proposed method estimates response timing by adding pseudo-samples where response should be irrelevant, which allows using text-only conversation dataset without audio information. Furthermore, our proposed method can control substantialness of responses by user-specified parameter integrated with the Dynamic-Prompt-Tune method, which uses prompt token embedding dynamically generated from the parameter. Our automatic and manual evaluation showed that the proposed method can generate responses with more natural timing and more in line with the response substantialness parameter compared to the baseline model.</p>

収録刊行物

詳細情報 詳細情報について

問題の指摘

ページトップへ