Fine-tuned edge ASR models reduce WER by 26.9 points over zero-shot baselines on 19 African languages while being substantially smaller and release supporting artifacts.
Findings of the Association for Computational Linguistics: ACL 2025 , year =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Four attention metrics enable logistic regression classifiers that detect hallucinations in SpeechLLMs with up to +0.23 PR-AUC gains over baselines on ASR and translation tasks.
citing papers explorer
-
WAXAL-NET: Finetuned Edge ASR Across 19 African Languages
Fine-tuned edge ASR models reduce WER by 26.9 points over zero-shot baselines on 19 African languages while being substantially smaller and release supporting artifacts.
-
Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps
Four attention metrics enable logistic regression classifiers that detect hallucinations in SpeechLLMs with up to +0.23 PR-AUC gains over baselines on ASR and translation tasks.