Zero-Shot Speech LLMs for Multi-Aspect Evaluation of L2 Speech: Challenges and Opportunities

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Parikh, Aditya Kamlesh, Tejedor-Garcia, Cristian, Cucchiarini, Catia, Strik, Helmer
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912842663329792
author Parikh, Aditya Kamlesh
Tejedor-Garcia, Cristian
Cucchiarini, Catia
Strik, Helmer
author_facet Parikh, Aditya Kamlesh
Tejedor-Garcia, Cristian
Cucchiarini, Catia
Strik, Helmer
contents An accurate assessment of L2 English pronunciation is crucial for language learning, as it provides personalized feedback and ensures a fair evaluation of individual progress. However, automated scoring remains challenging due to the complexity of sentence-level fluency, prosody, and completeness. This paper evaluates the zero-shot performance of Qwen2-Audio-7B-Instruct, an instruction-tuned speech-LLM, on 5,000 Speechocean762 utterances. The model generates rubric-aligned scores for accuracy, fluency, prosody, and completeness, showing strong agreement with human ratings within +-2 tolerance, especially for high-quality speech. However, it tends to overpredict low-quality speech scores and lacks precision in error detection. These findings demonstrate the strong potential of speech LLMs in scalable pronunciation assessment and suggest future improvements through enhanced prompting, calibration, and phonetic integration to advance Computer-Assisted Pronunciation Training.
format Preprint
id arxiv_https___arxiv_org_abs_2601_16230
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Zero-Shot Speech LLMs for Multi-Aspect Evaluation of L2 Speech: Challenges and Opportunities
Parikh, Aditya Kamlesh
Tejedor-Garcia, Cristian
Cucchiarini, Catia
Strik, Helmer
Audio and Speech Processing
Artificial Intelligence
Computation and Language
Sound
An accurate assessment of L2 English pronunciation is crucial for language learning, as it provides personalized feedback and ensures a fair evaluation of individual progress. However, automated scoring remains challenging due to the complexity of sentence-level fluency, prosody, and completeness. This paper evaluates the zero-shot performance of Qwen2-Audio-7B-Instruct, an instruction-tuned speech-LLM, on 5,000 Speechocean762 utterances. The model generates rubric-aligned scores for accuracy, fluency, prosody, and completeness, showing strong agreement with human ratings within +-2 tolerance, especially for high-quality speech. However, it tends to overpredict low-quality speech scores and lacks precision in error detection. These findings demonstrate the strong potential of speech LLMs in scalable pronunciation assessment and suggest future improvements through enhanced prompting, calibration, and phonetic integration to advance Computer-Assisted Pronunciation Training.
title Zero-Shot Speech LLMs for Multi-Aspect Evaluation of L2 Speech: Challenges and Opportunities
topic Audio and Speech Processing
Artificial Intelligence
Computation and Language
Sound
url https://arxiv.org/abs/2601.16230