Saved in:
Bibliographic Details
Main Authors: Han, Hong, Pei, Hao-Chen, Nie, Zhao-Zheng, Luo, Xin, Xu, Xin-Shun
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.01745
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915708017836032
author Han, Hong
Pei, Hao-Chen
Nie, Zhao-Zheng
Luo, Xin
Xu, Xin-Shun
author_facet Han, Hong
Pei, Hao-Chen
Nie, Zhao-Zheng
Luo, Xin
Xu, Xin-Shun
contents Automatic pronunciation assessment plays a crucial role in computer-assisted pronunciation training systems. Due to the ability to perform multiple pronunciation tasks simultaneously, multi-aspect multi-granularity pronunciation assessment methods are gradually receiving more attention and achieving better performance than single-level modeling tasks. However, existing methods only consider unidirectional dependencies between adjacent granularity levels, lacking bidirectional interaction among phoneme, word, and utterance levels and thus insufficiently capturing the acoustic structural correlations. To address this issue, we propose a novel residual hierarchical interactive method, HIA for short, that enables bidirectional modeling across granularities. As the core of HIA, the Interactive Attention Module leverages an attention mechanism to achieve dynamic bidirectional interaction, effectively capturing linguistic features at each granularity while integrating correlations between different granularity levels. We also propose a residual hierarchical structure to alleviate the feature forgetting problem when modeling acoustic hierarchies. In addition, we use 1-D convolutional layers to enhance the extraction of local contextual cues at each granularity. Extensive experiments on the speechocean762 dataset show that our model is comprehensively ahead of the existing state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2601_01745
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-granularity Interactive Attention Framework for Residual Hierarchical Pronunciation Assessment
Han, Hong
Pei, Hao-Chen
Nie, Zhao-Zheng
Luo, Xin
Xu, Xin-Shun
Computation and Language
Artificial Intelligence
Automatic pronunciation assessment plays a crucial role in computer-assisted pronunciation training systems. Due to the ability to perform multiple pronunciation tasks simultaneously, multi-aspect multi-granularity pronunciation assessment methods are gradually receiving more attention and achieving better performance than single-level modeling tasks. However, existing methods only consider unidirectional dependencies between adjacent granularity levels, lacking bidirectional interaction among phoneme, word, and utterance levels and thus insufficiently capturing the acoustic structural correlations. To address this issue, we propose a novel residual hierarchical interactive method, HIA for short, that enables bidirectional modeling across granularities. As the core of HIA, the Interactive Attention Module leverages an attention mechanism to achieve dynamic bidirectional interaction, effectively capturing linguistic features at each granularity while integrating correlations between different granularity levels. We also propose a residual hierarchical structure to alleviate the feature forgetting problem when modeling acoustic hierarchies. In addition, we use 1-D convolutional layers to enhance the extraction of local contextual cues at each granularity. Extensive experiments on the speechocean762 dataset show that our model is comprehensively ahead of the existing state-of-the-art methods.
title Multi-granularity Interactive Attention Framework for Residual Hierarchical Pronunciation Assessment
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2601.01745