Dialogue Response Prefetching Based on Semantic Similarity and Prediction Confidence of Language Model

Kiyotada Mori, Seiya Kawano, Angel Fernando Garcia Contreras, Koichiro Yoshino
8/6/2025
cs.CL

No confident code implementation found for this paper.

Abstract

Prefetching of dialogue responses has been investigated to reduce user-perceived latency (UPL), which refers to the user's waiting time before receiving the system's response, in spoken dialogue systems. To reduce the UPL, it is necessary to predict complete user utterances before the end of the user's speech, typically by language models, to prepare prefetched dialogue responses. In this study, we proposed a prediction confidence model (PCM) that determines whether prefetching is possible or not by estimating the semantic similarity between the predicted complete user utterance and the complete user utterance. We evaluated our PCM based on the differences between the predicted complete user utterance and the complete user utterance.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

PredGen: Accelerated Inference of Large Language Models through Input-Time Speculation for Real-Time Speech Interaction

84% match2025

SayNext-Bench: Why Do LLMs Struggle with Next-Utterance Prediction?

81% match2026

Human Latency Conversational Turns for Spoken Avatar Systems

81% match2024

Predictive Speech Recognition and End-of-Utterance Detection Towards Spoken Dialog Systems

79% match2024

Large Language Models Know What To Say But Not When To Speak

78% match2024

Learning to Simulate Human Dialogue

78% match2026

Cite this paper

@article{mori2025dialogue,
  title  = {Dialogue Response Prefetching Based on Semantic Similarity and Prediction Confidence of Language Model},
  author = {Kiyotada Mori and Seiya Kawano and Angel Fernando Garcia Contreras and Koichiro Yoshino},
  year   = {2025},
  eprint = {2508.04403},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.04403v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.04403.svg)](https://codeofpaper.com/paper/2508.04403)

Discussion