← Search

Heereen Shim

2 accepted papers

2025

Lightweight neural front-ends for low-resource on-device Text-to-Speech

ICASSP 2025accepted

We propose a lightweight neural front-end framework for on-device speech generation and highlight its benefits towards low-resource language scaling. While data-driven models have shown potential in front-end literature, especially since they can enable fast language expansion, they are often extrem…

Cited by 0SourceScholar
2022

Data-Efficient Algorithms and Neural Natural Language Processing: Applications in the Healthcare Domain

IJCAI 2022poster

Recently proposed pre-trained language models can be easily fine-tuned to a wide range of downstream tasks. However, fine-tuning requires a large training set. This PhD project introduces novel natural language processing (NLP) use cases in the healthcare domain where obtaining a large training data…

Cited by 1SourcePDFScholar