Graph Connectionist Temporal Classification for Phoneme Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914025595469824 |
|---|---|
| author | Grafé, Henry Van hamme, Hugo |
| author_facet | Grafé, Henry Van hamme, Hugo |
| contents | Automatic Phoneme Recognition (APR) systems are often trained using pseudo phoneme-level annotations generated from text through Grapheme-to-Phoneme (G2P) systems. These G2P systems frequently output multiple possible pronunciations per word, but the standard Connectionist Temporal Classification (CTC) loss cannot account for such ambiguity during training. In this work, we adapt Graph Temporal Classification (GTC) to the APR setting. GTC enables training from a graph of alternative phoneme sequences, allowing the model to consider multiple pronunciations per word as valid supervision. Our experiments on English and Dutch data sets show that incorporating multiple pronunciations per word into the training loss consistently improves phoneme error rates compared to a baseline trained with CTC. These results suggest that integrating pronunciation variation into the loss function is a promising strategy for training APR systems from noisy G2P-based supervision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_05399 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Graph Connectionist Temporal Classification for Phoneme Recognition Grafé, Henry Van hamme, Hugo Audio and Speech Processing Artificial Intelligence 68T10, 68T07 I.2.7; I.5.4; H.5.1 Automatic Phoneme Recognition (APR) systems are often trained using pseudo phoneme-level annotations generated from text through Grapheme-to-Phoneme (G2P) systems. These G2P systems frequently output multiple possible pronunciations per word, but the standard Connectionist Temporal Classification (CTC) loss cannot account for such ambiguity during training. In this work, we adapt Graph Temporal Classification (GTC) to the APR setting. GTC enables training from a graph of alternative phoneme sequences, allowing the model to consider multiple pronunciations per word as valid supervision. Our experiments on English and Dutch data sets show that incorporating multiple pronunciations per word into the training loss consistently improves phoneme error rates compared to a baseline trained with CTC. These results suggest that integrating pronunciation variation into the loss function is a promising strategy for training APR systems from noisy G2P-based supervision. |
| title | Graph Connectionist Temporal Classification for Phoneme Recognition |
| topic | Audio and Speech Processing Artificial Intelligence 68T10, 68T07 I.2.7; I.5.4; H.5.1 |
| url | https://arxiv.org/abs/2509.05399 |