Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Guan-Ting, Lian, Jiachen, Li, Tingle, Wang, Qirui, Anumanchipalli, Gopala, Liu, Alexander H., Lee, Hung-yi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915447810555904
author Lin, Guan-Ting
Lian, Jiachen
Li, Tingle
Wang, Qirui
Anumanchipalli, Gopala
Liu, Alexander H.
Lee, Hung-yi
author_facet Lin, Guan-Ting
Lian, Jiachen
Li, Tingle
Wang, Qirui
Anumanchipalli, Gopala
Liu, Alexander H.
Lee, Hung-yi
contents Spoken dialogue modeling poses challenges beyond text-based language modeling, requiring real-time interaction, turn-taking, and backchanneling. While most Spoken Dialogue Models (SDMs) operate in half-duplex mode-processing one turn at a time - emerging full-duplex SDMs can listen and speak simultaneously, enabling more natural conversations. However, current evaluations remain limited, focusing mainly on turn-based metrics or coarse corpus-level analyses. To address this, we introduce Full-Duplex-Bench, a benchmark that systematically evaluates key interactive behaviors: pause handling, backchanneling, turn-taking, and interruption management. Our framework uses automatic metrics for consistent, reproducible assessment and provides a fair, fast evaluation setup. By releasing our benchmark and code, we aim to advance spoken dialogue modeling and foster the development of more natural and engaging SDMs.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04721
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities
Lin, Guan-Ting
Lian, Jiachen
Li, Tingle
Wang, Qirui
Anumanchipalli, Gopala
Liu, Alexander H.
Lee, Hung-yi
Computation and Language
Audio and Speech Processing
Spoken dialogue modeling poses challenges beyond text-based language modeling, requiring real-time interaction, turn-taking, and backchanneling. While most Spoken Dialogue Models (SDMs) operate in half-duplex mode-processing one turn at a time - emerging full-duplex SDMs can listen and speak simultaneously, enabling more natural conversations. However, current evaluations remain limited, focusing mainly on turn-based metrics or coarse corpus-level analyses. To address this, we introduce Full-Duplex-Bench, a benchmark that systematically evaluates key interactive behaviors: pause handling, backchanneling, turn-taking, and interruption management. Our framework uses automatic metrics for consistent, reproducible assessment and provides a fair, fast evaluation setup. By releasing our benchmark and code, we aim to advance spoken dialogue modeling and foster the development of more natural and engaging SDMs.
title Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities
topic Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2503.04721