Saved in:
Bibliographic Details
Main Authors: Mori, Kiyotada, Kawano, Seiya, Contreras, Angel Fernando Garcia, Yoshino, Koichiro
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.04403
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915725006864384
author Mori, Kiyotada
Kawano, Seiya
Contreras, Angel Fernando Garcia
Yoshino, Koichiro
author_facet Mori, Kiyotada
Kawano, Seiya
Contreras, Angel Fernando Garcia
Yoshino, Koichiro
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04403
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dialogue Response Prefetching Based on Semantic Similarity and Prediction Confidence of Language Model
Mori, Kiyotada
Kawano, Seiya
Contreras, Angel Fernando Garcia
Yoshino, Koichiro
Computation and Language
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.
title Dialogue Response Prefetching Based on Semantic Similarity and Prediction Confidence of Language Model
topic Computation and Language
url https://arxiv.org/abs/2508.04403