Adapting Foundational ASR Models to Efik: An Empirical Study of an Extremely Low-Resource Tonal Language

Record type:

paper

Creator:

OffSteEnoBen

Publisher:

Eur

Host:

Visit

doi.org

Tasks

automatic speech recognition speech processing

Pretraining Language Models with Subword Regularization: An Empirical Study of BPE Dropout in Low-Resource NLP

Subword regularization methods such as BPE dropout are typically applied only during fine-tuning, wh

Specializing Multilingual Language Models: An Empirical Study

Pretrained multilingual language models have become a common tool in transferring NLP capabilities t

Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languages

Automatic Speech Recognition (ASR) has reached impressive accuracy for high-resource languages, yet

Effective vocabulary expansion of multilingual language models for extremely low-resource languages

Multilingual pre-trained language models(mPLMs) offer significant benefits for many low-resource lan

Adapting Large Language Models to Low-Resource Tibetan: A Two-Stage Continual and Supervised Fine-Tuning Study

Adapting large language models (LLMs) to low-resource languages remains a major challenge due to dat

The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation

A “bigger is better” explosion in the number of parameters in deep neural networks has made it increasingly challenging to make state-of-the-art networks accessible in compute-restricted environments. Compression techniques have taken on renewed importance as a way