Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Ke, He, Lei, Liu, Kun, Deng, Yan, Wei, Wenning, Zhao, Sheng
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.11229
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929759824379904
author Wang, Ke
He, Lei
Liu, Kun
Deng, Yan
Wei, Wenning
Zhao, Sheng
author_facet Wang, Ke
He, Lei
Liu, Kun
Deng, Yan
Wei, Wenning
Zhao, Sheng
contents Large Multimodal Models (LMMs) have demonstrated exceptional performance across a wide range of domains. This paper explores their potential in pronunciation assessment tasks, with a particular focus on evaluating the capabilities of the Generative Pre-trained Transformer (GPT) model, specifically GPT-4o. Our study investigates its ability to process speech and audio for pronunciation assessment across multiple levels of granularity and dimensions, with an emphasis on feedback generation and scoring. For our experiments, we use the publicly available Speechocean762 dataset. The evaluation focuses on two key aspects: multi-level scoring and the practicality of the generated feedback. Scoring results are compared against the manual scores provided in the Speechocean762 dataset, while feedback quality is assessed using Large Language Models (LLMs). The findings highlight the effectiveness of integrating LMMs with traditional methods for pronunciation assessment, offering insights into the model's strengths and identifying areas for further improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2503_11229
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring the Potential of Large Multimodal Models as Effective Alternatives for Pronunciation Assessment
Wang, Ke
He, Lei
Liu, Kun
Deng, Yan
Wei, Wenning
Zhao, Sheng
Sound
Computation and Language
Audio and Speech Processing
Large Multimodal Models (LMMs) have demonstrated exceptional performance across a wide range of domains. This paper explores their potential in pronunciation assessment tasks, with a particular focus on evaluating the capabilities of the Generative Pre-trained Transformer (GPT) model, specifically GPT-4o. Our study investigates its ability to process speech and audio for pronunciation assessment across multiple levels of granularity and dimensions, with an emphasis on feedback generation and scoring. For our experiments, we use the publicly available Speechocean762 dataset. The evaluation focuses on two key aspects: multi-level scoring and the practicality of the generated feedback. Scoring results are compared against the manual scores provided in the Speechocean762 dataset, while feedback quality is assessed using Large Language Models (LLMs). The findings highlight the effectiveness of integrating LMMs with traditional methods for pronunciation assessment, offering insights into the model's strengths and identifying areas for further improvement.
title Exploring the Potential of Large Multimodal Models as Effective Alternatives for Pronunciation Assessment
topic Sound
Computation and Language
Audio and Speech Processing
url https://arxiv.org/abs/2503.11229