Papers by Thennal D K
Advocating Character Error Rate for Multilingual ASR Evaluation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Word error rate (WER) has been used for automatic speech recognition (ASR) evaluations for English datasets for many years. |
| Approach: | They propose to use the character error rate as the primary metric in multilingual ASR evaluation to account for morphologically complex languages. |
| Outcome: | The character error rate (CER) is the primary evaluation metric in multilingual ASR evaluation. |
Just Use XML: Revisiting Joint Translation and Label Projection (2026.findings-acl)
Copied to clipboard
| Challenge: | Label projection is an effective technique for cross-lingual transfer, extending span-annotated datasets from high-resource languages to low-resourced ones. |
| Approach: | They propose a framework that performs translation and label projection via XML tags. |
| Outcome: | The proposed framework outperforms baselines and improves translation quality across languages and annotation complexity. |