MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, He, Cui, Wenqian, Xu, Haoning, Li, Xiaohui, Zhu, Lei, Bai, Haoli, Ma, Shaohua, King, Irwin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917414840565760
author Zhang, He
Cui, Wenqian
Xu, Haoning
Li, Xiaohui
Zhu, Lei
Bai, Haoli
Ma, Shaohua
King, Irwin
author_facet Zhang, He
Cui, Wenqian
Xu, Haoning
Li, Xiaohui
Zhu, Lei
Bai, Haoli
Ma, Shaohua
King, Irwin
contents Full-Duplex Speech Language Models (FD-SLMs) enable real-time, overlapping conversational interactions, offering a more dynamic user experience compared to traditional half-duplex models. However, existing benchmarks primarily focus on evaluating single-round interactions, neglecting the complexities of multi-round communication. Evaluating FD-SLMs in multi-round settings poses significant challenges, including blurred turn boundaries in communication and context inconsistency during model inference. Also, existing benchmarks often focus solely on evaluating conversational features, neglecting other critical aspects. To address these gaps, we introduce MTR-DuplexBench, a novel benchmark designed for a comprehensive multi-round evaluation of FD-SLMs. MTR-DuplexBench not only segments continuous full-duplex dialogues into discrete turns for turn-by-turn assessment but also incorporates various evaluation aspects, including conversational features, dialogue quality, instruction following, and safety. Experimental results reveal that current FD-SLMs face difficulties in maintaining consistent performance across multiple rounds and evaluation dimensions, highlighting the necessity and effectiveness of our benchmark. Code and data are available at: https://github.com/ZhangHe0918/MTR-DuplexBench
format Preprint
id arxiv_https___arxiv_org_abs_2511_10262
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models
Zhang, He
Cui, Wenqian
Xu, Haoning
Li, Xiaohui
Zhu, Lei
Bai, Haoli
Ma, Shaohua
King, Irwin
Computation and Language
Artificial Intelligence
Audio and Speech Processing
Full-Duplex Speech Language Models (FD-SLMs) enable real-time, overlapping conversational interactions, offering a more dynamic user experience compared to traditional half-duplex models. However, existing benchmarks primarily focus on evaluating single-round interactions, neglecting the complexities of multi-round communication. Evaluating FD-SLMs in multi-round settings poses significant challenges, including blurred turn boundaries in communication and context inconsistency during model inference. Also, existing benchmarks often focus solely on evaluating conversational features, neglecting other critical aspects. To address these gaps, we introduce MTR-DuplexBench, a novel benchmark designed for a comprehensive multi-round evaluation of FD-SLMs. MTR-DuplexBench not only segments continuous full-duplex dialogues into discrete turns for turn-by-turn assessment but also incorporates various evaluation aspects, including conversational features, dialogue quality, instruction following, and safety. Experimental results reveal that current FD-SLMs face difficulties in maintaining consistent performance across multiple rounds and evaluation dimensions, highlighting the necessity and effectiveness of our benchmark. Code and data are available at: https://github.com/ZhangHe0918/MTR-DuplexBench
title MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models
topic Computation and Language
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2511.10262