Saved in:
Bibliographic Details
Main Authors: Zhang, Linhao, Zhang, Jian, Lei, Bokai, Wu, Chuhan, Liu, Aiwei, Jia, Wei, Zhou, Xiao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.21875
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918148572184576
author Zhang, Linhao
Zhang, Jian
Lei, Bokai
Wu, Chuhan
Liu, Aiwei
Jia, Wei
Zhou, Xiao
author_facet Zhang, Linhao
Zhang, Jian
Lei, Bokai
Wu, Chuhan
Liu, Aiwei
Jia, Wei
Zhou, Xiao
contents Recent multi-modal Large Language Models (LLMs) such as GPT-4o have demonstrated strong capabilities of direct speech interaction. However, the lack of specialized and comprehensive benchmarks for end-to-end speech LLM evaluation hinders optimizing the user experience of Audio LLMs in real-world applications. Existing evaluation methods often adapt text-based benchmarks, overlooking speech's unique characteristics and challenges, including prosody, homophones, stuttering, and differing user expectations. Here, we introduce the first comprehensive benchmark designed to systematically evaluate end-to-end speechLLMs in practical speech conversations. We systematically curate real-world chat data relevant to spoken scenarios, introduce diversity in speaker attributes and acoustic conditions, and augment the dataset with speech-specific phenomena. We further design a query-aware evaluation method to use customized evaluation checklists and prompts to enhance the accuracy of automatic evaluation. We conduct comprehensive testing and detailed analysis of various mainstream speech models, revealing significant differences in model performance across different speech scenarios. The use of query-aware evaluation further enables a finer-grained assessment under various speech-specific scenarios. Our benchmark can provide valuable insights for speech model development and evaluation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21875
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle WildSpeech-Bench: Benchmarking End-to-End SpeechLLMs in the Wild
Zhang, Linhao
Zhang, Jian
Lei, Bokai
Wu, Chuhan
Liu, Aiwei
Jia, Wei
Zhou, Xiao
Computation and Language
Recent multi-modal Large Language Models (LLMs) such as GPT-4o have demonstrated strong capabilities of direct speech interaction. However, the lack of specialized and comprehensive benchmarks for end-to-end speech LLM evaluation hinders optimizing the user experience of Audio LLMs in real-world applications. Existing evaluation methods often adapt text-based benchmarks, overlooking speech's unique characteristics and challenges, including prosody, homophones, stuttering, and differing user expectations. Here, we introduce the first comprehensive benchmark designed to systematically evaluate end-to-end speechLLMs in practical speech conversations. We systematically curate real-world chat data relevant to spoken scenarios, introduce diversity in speaker attributes and acoustic conditions, and augment the dataset with speech-specific phenomena. We further design a query-aware evaluation method to use customized evaluation checklists and prompts to enhance the accuracy of automatic evaluation. We conduct comprehensive testing and detailed analysis of various mainstream speech models, revealing significant differences in model performance across different speech scenarios. The use of query-aware evaluation further enables a finer-grained assessment under various speech-specific scenarios. Our benchmark can provide valuable insights for speech model development and evaluation.
title WildSpeech-Bench: Benchmarking End-to-End SpeechLLMs in the Wild
topic Computation and Language
url https://arxiv.org/abs/2506.21875