ASR Error Correction in Low-Resource Burmese with Alignment-Enhanced Transformers using Phonetic Features
It addresses ASR error correction for Burmese, a low-resource language, but is incremental as it applies known methods with new feature combinations.
This paper tackled ASR error correction for low-resource Burmese by integrating phonetic and alignment features into Transformers, reducing average WER from 51.56 to 39.82 and improving chrF++ scores from 0.5864 to 0.627.
This paper investigates sequence-to-sequence Transformer models for automatic speech recognition (ASR) error correction in low-resource Burmese, focusing on different feature integration strategies including IPA and alignment information. To our knowledge, this is the first study addressing ASR error correction specifically for Burmese. We evaluate five ASR backbones and show that our ASR Error Correction (AEC) approaches consistently improve word- and character-level accuracy over baseline outputs. The proposed AEC model, combining IPA and alignment features, reduced the average WER of ASR models from 51.56 to 39.82 before augmentation (and 51.56 to 43.59 after augmentation) and improving chrF++ scores from 0.5864 to 0.627, demonstrating consistent gains over the baseline ASR outputs without AEC. Our results highlight the robustness of AEC and the importance of feature design for improving ASR outputs in low-resource settings.