4 papers
Easper: An Accessible ASR Pipeline for Language Documentation
Aso Mahmudi, Ting Dang, Ekaterina Vylomova +1
Audio transcription is a critical bottleneck in language documentation. While multilingual Automatic Speech Recognition (ASR) models like Whisper offer solutions, field linguists o…
QuaSR: Quality-Aware Sample Reweighting for Pacific Indigenous Speech Recognition
Yishun Li, Yang Xiao, Gongping Huang +3
Training automatic speech recognition (ASR) models for low-resource languages is challenging due to limited data and highly variable supervision quality. In particular, Pacific Ind…
Continual Adaptation for Pacific Indigenous Speech Recognition
Yang Xiao, Aso Mahmudi, Nick Thieberger +3
Speech foundation models struggle with low-resource Pacific Indigenous languages because of severe data scarcity. Furthermore, full fine-tuning risks catastrophic forgetting. To ad…
TULUN: Transparent and Adaptable Low-resource Machine Translation
Raphaël Merx, Hanna Suominen, Lois Hong +3
Machine translation (MT) systems that support low-resource languages often struggle on specialized domains. While researchers have proposed various techniques for domain adaptation…