Year: 2025
Type: preprint
Abstract: Automatic speech recognition (ASR) is critical for language accessibility, yet low-resource Cantonese remains challenging due to limited annotated data, six lexical tones, tone sandhi, and accent variation. Existing ASR models, such as Whisper, often suffer from high word error rates. Large audio-language models (LALMs), in contrast, can leverage broader contextual reasoning but still require explicit tonal and prosodic acoustic cues. We introduce CantoASR, a collaborative ASR-LALM error correction framework that integrates forced alignment for acoustic feature extraction, a LoRA-finetuned Whisper for improved tone discrimination, and an instruction-tuned Qwen-Audio for prosody-aware correction. Evaluations on spontaneous Cantonese data show substantial CER gains over Whisper-Large-V3. These findings suggest that integrating acoustic cues with LALM reasoning provides a scalable strategy for low-resource tonal and dialectal ASR.
Source: arXiv (Cornell University)
Authors: Chen, Dazhong, Lin, Yi-Cheng, Huang, Yuchen, Gong, Ziwei, Jiang, Di, Xie, Zeying, R., Yi, Fung
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4416024010
Cites:
Cited by:
Related to: