Blank-Aware Decoding for Transcript-Free Phoneme Alignment in Low-Resource Languages and Dialects
Proceedings of Speech Language Models in Low-Resource Settings: Performance, Evaluation, and Bias Analysis (SPEAKABLE) @ LREC 2026
Abstract
We present a blank-aware decoding approach for transcript-free phoneme alignment with CTC-based speech foundation models, designed to improve annotation bootstrapping in low-resource languages. While CTC models provide frame-level phoneme posteriors without requiring transcripts, greedy decoding produces blank-dominated and temporally unstable segmentations that are difficult to correct manually. Our approach introduces two training-free blank-resolution strategies operating directly on CTC logits: (i) confidence-ratio substitution, which promotes competitive non-blank hypotheses relative to the blank symbol, and (ii) recursive context adjustment, which enforces local contextual consistency within blank spans. Experiments on English (TIMIT) and on Sardinian and Tyrolean dialect corpora show consistent improvements in boundary F1 prediction, phoneme duration regularity, and segmentation stability over greedy CTC decoding. Although absolute boundary deviations remain higher than transcript-conditioned aligners, the resulting alignments are structurally coherent and suitable for manual correction. A post-hoc phoneme-class analysis further reveals systematic asymmetries in blank resolution, highlighting complementary roles of local acoustic evidence and contextual cues, and outlining prominising venues for future improvements.