Author

Srishti Ginjala

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Preprint Sep 2026

Fairness Beyond a Single Run: Training-Seed Variability in Speech LLM Adaptation

At 460 h of clean LibriSpeech, the seed moves fairness metrics more than compression does on most demographic axes, and a balanced 3x3 decomposition attributes 85.3% of the variation in Fair-Speech ethnicity normalized gap to the seed against 8.3% to compression.

Srishti Ginjala, E. Fosler-Lussier, Srinivasan Parthasarathy · 0 citations

#natural language process... Preprint Sep 2026

Temporal Taxation Compounds Under Post-Training Compression of Whisper Models

It is shown that single-snapshot fairness audits on full-precision models do not capture the deployment-time burden that compression places on already-marginalized speakers, and cast the temporal-taxation construct of Choi and Choi (2025) as a quantitative metric.

Srishti Ginjala, E. Fosler-Lussier, Christopher W. Myers et al. · 0 citations