Full-Duplex Interaction in Spoken Dialogue Systems: A Comprehensive Study from the ICASSP 2026 HumDial Challenge

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Chengyou, Xue, Hongfei, Li, Guojian, Zhao, Zhixian, Wang, Shuiyuan, Wang, Shuai, Xu, Xin, Bu, Hui, Xie, Lei
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908990780211200
author Wang, Chengyou
Xue, Hongfei
Li, Guojian
Zhao, Zhixian
Wang, Shuiyuan
Wang, Shuai
Xu, Xin
Bu, Hui
Xie, Lei
author_facet Wang, Chengyou
Xue, Hongfei
Li, Guojian
Zhao, Zhixian
Wang, Shuiyuan
Wang, Shuai
Xu, Xin
Bu, Hui
Xie, Lei
contents Full-duplex interaction, where speakers and listeners converse simultaneously, is a key element of human communication often missing from traditional spoken dialogue systems. These systems, based on rigid turn-taking paradigms, struggle to respond naturally in dynamic conversations. The Full-Duplex Interaction Track of ICASSP 2026 Human-like Spoken Dialogue Systems Challenge (HumDial Challenge) aims to advance the evaluation of full-duplex systems by offering a framework for handling real-time interruptions, speech overlap, and dynamic turn negotiation. We introduce a comprehensive benchmark for full-duplex spoken dialogue systems, built from the HumDial Challenge. We release a high-quality dual-channel dataset of real human-recorded conversations, capturing interruptions, overlapping speech, and feedback mechanisms. This dataset forms the basis for the HumDial-FDBench benchmark, which assesses a system's ability to handle interruptions while maintaining conversational flow. Additionally, we create a public leaderboard to compare the performance of open-source and proprietary models, promoting transparent, reproducible evaluation. These resources support the development of more responsive, adaptive, and human-like dialogue systems.
format Preprint
id arxiv_https___arxiv_org_abs_2604_21406
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Full-Duplex Interaction in Spoken Dialogue Systems: A Comprehensive Study from the ICASSP 2026 HumDial Challenge
Wang, Chengyou
Xue, Hongfei
Li, Guojian
Zhao, Zhixian
Wang, Shuiyuan
Wang, Shuai
Xu, Xin
Bu, Hui
Xie, Lei
Audio and Speech Processing
Full-duplex interaction, where speakers and listeners converse simultaneously, is a key element of human communication often missing from traditional spoken dialogue systems. These systems, based on rigid turn-taking paradigms, struggle to respond naturally in dynamic conversations. The Full-Duplex Interaction Track of ICASSP 2026 Human-like Spoken Dialogue Systems Challenge (HumDial Challenge) aims to advance the evaluation of full-duplex systems by offering a framework for handling real-time interruptions, speech overlap, and dynamic turn negotiation. We introduce a comprehensive benchmark for full-duplex spoken dialogue systems, built from the HumDial Challenge. We release a high-quality dual-channel dataset of real human-recorded conversations, capturing interruptions, overlapping speech, and feedback mechanisms. This dataset forms the basis for the HumDial-FDBench benchmark, which assesses a system's ability to handle interruptions while maintaining conversational flow. Additionally, we create a public leaderboard to compare the performance of open-source and proprietary models, promoting transparent, reproducible evaluation. These resources support the development of more responsive, adaptive, and human-like dialogue systems.
title Full-Duplex Interaction in Spoken Dialogue Systems: A Comprehensive Study from the ICASSP 2026 HumDial Challenge
topic Audio and Speech Processing
url https://arxiv.org/abs/2604.21406