English

Syllabic-Structure Decoder for Automatic Speech Recognition in Vietnamese

Computation and Language 2026-05-28 v1

Abstract

Most Automatic Speech Recognition (ASR) systems formulate transcription as a prediction problem over orthographic units such as characters, subwords, or words. Although effective, such representations do not explicitly reflect the phonetic structure of speech and often require large vocabularies to maintain adequate coverage. In this work, we are motivated from the phonemic features of Vietnamese to propose a Syllabic-Structure Decoder for ASR, which models speech at the phoneme level instead of the orthographic level. Our approach explicitly captures the phonological composition of syllables, enabling the decoder to generate valid syllabic structures from a compact phonemic inventory. This design more closely aligns with the phonetic realization of speech while significantly reducing vocabulary size. Experimental results on two benchmarks: LSVSC, representing standard speech, and UIT-ViMD, a multi-dialect corpus containing diverse regional pronunciations, show that our method consistently outperforms strong previous baselines, especially pretrained baselines such as PhoWhisper and Wav2Vec2, despite using a substantially smaller vocabulary and no additional training resources. These results highlight the effectiveness of phoneme-based syllabic modeling for ASR in this language. Code for experimental reproducibility will be publicly available upon the acceptance of this paper.

Keywords

Cite

@article{arxiv.2605.27874,
  title  = {Syllabic-Structure Decoder for Automatic Speech Recognition in Vietnamese},
  author = {Nghia Hieu Nguyen and Quan Ngoc Hoang and Long Hoang Huu Nguyen and Kiet Van Nguyen and Ngan Luu-Thuy Nguyen},
  journal= {arXiv preprint arXiv:2605.27874},
  year   = {2026}
}