SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Hui, Zhao, Jinghua, Yang, Yifan, Liu, Shujie, Chen, Junyang, Zhang, Yanzhe, Zhao, Shiwan, Li, Jinyu, Zhou, Jiaming, Sun, Haoqin, Lu, Yan, Qin, Yong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908968901672960
author Wang, Hui
Zhao, Jinghua
Yang, Yifan
Liu, Shujie
Chen, Junyang
Zhang, Yanzhe
Zhao, Shiwan
Li, Jinyu
Zhou, Jiaming
Sun, Haoqin
Lu, Yan
Qin, Yong
author_facet Wang, Hui
Zhao, Jinghua
Yang, Yifan
Liu, Shujie
Chen, Junyang
Zhang, Yanzhe
Zhao, Shiwan
Li, Jinyu
Zhou, Jiaming
Sun, Haoqin
Lu, Yan
Qin, Yong
contents Generative speech technologies are progressing rapidly, but evaluating the perceptual quality of synthetic speech remains a core challenge. Existing methods typically rely on scalar scores or binary decisions, which lack interpretability and generalization across tasks and languages. We present SpeechLLM-as-Judges, a new paradigm for enabling large language models (LLMs) to conduct structured and explanation-based speech quality evaluation. To support this direction, we introduce SpeechEval, a large-scale dataset containing 32,207 multilingual speech clips and 128,754 annotations spanning four tasks: quality assessment, pairwise comparison, improvement suggestion, and deepfake detection. Based on this resource, we develop SQ-LLM, a speech-quality-aware LLM trained with chain-of-thought reasoning and reward optimization to improve capability. Experimental results show that SQ-LLM delivers strong performance across tasks and languages, revealing the potential of this paradigm for advancing speech quality evaluation. The relevant code, models, and data are publicly available at https://github.com/NKU-HLT/SpeechLLM-as-Judges.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14664
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation
Wang, Hui
Zhao, Jinghua
Yang, Yifan
Liu, Shujie
Chen, Junyang
Zhang, Yanzhe
Zhao, Shiwan
Li, Jinyu
Zhou, Jiaming
Sun, Haoqin
Lu, Yan
Qin, Yong
Sound
Audio and Speech Processing
Generative speech technologies are progressing rapidly, but evaluating the perceptual quality of synthetic speech remains a core challenge. Existing methods typically rely on scalar scores or binary decisions, which lack interpretability and generalization across tasks and languages. We present SpeechLLM-as-Judges, a new paradigm for enabling large language models (LLMs) to conduct structured and explanation-based speech quality evaluation. To support this direction, we introduce SpeechEval, a large-scale dataset containing 32,207 multilingual speech clips and 128,754 annotations spanning four tasks: quality assessment, pairwise comparison, improvement suggestion, and deepfake detection. Based on this resource, we develop SQ-LLM, a speech-quality-aware LLM trained with chain-of-thought reasoning and reward optimization to improve capability. Experimental results show that SQ-LLM delivers strong performance across tasks and languages, revealing the potential of this paradigm for advancing speech quality evaluation. The relevant code, models, and data are publicly available at https://github.com/NKU-HLT/SpeechLLM-as-Judges.
title SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2510.14664