4 papers
Something from Nothing: Data Augmentation for Robust Severity Level Estimation of Dysarthric Speech
Jaesung Bae, Xiuwen Zheng, Minje Kim +2
Dysarthric speech quality assessment (DSQA) is critical for clinical diagnostics and inclusive speech technologies. However, subjective evaluation is costly and difficult to scale,…
Semantics-Aware Generative Latent Data Augmentation for Learning in Low-Resource Domains
Jaesung Bae, Minje Kim
Despite strong performance in data-rich regimes, deep learning often underperforms in the data-scarce settings common in practice. While foundation models (FMs) trained on massive…
That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation
Jaesung Bae, Cameron Churchwell, Mitchell Hermon +5
This paper investigates how large language models (LLMs) behave when faced with discrepancies between their parametric knowledge and conflicting information contained in a prompt.…
Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement
Jae-Sung Bae, Anastasia Kuznetsova, Dinesh Manocha +3
This paper presents a new challenge that calls for zero-shot text-to-speech (TTS) systems to augment speech data for the downstream task, personalized speech enhancement (PSE), as…