2 papers
cs.LG2026
Disentangling Algorithmic Bias from Archival Artifacts: A Controlled Audit of Vision-Language Model Valuation in Metropolitan Museum Archives
Manpreet Singh, Rhythm Bhatia, Rahul Joshi
Auditing vision-language models (VLMs) for societal bias requires distinguishing direct algorithmic valuation disparities from confounders embedded within archival metadata. In thi…
eess.AS2022
An Initial study on Birdsong Re-synthesis Using Neural Vocoders
Rhythm Bhatia, Tomi H. Kinnunen
Modern speech synthesis uses neural vocoders to model raw waveform samples directly. This increased versatility has expanded the scope of vocoders from speech to other domains, suc…