Aparna Srinivasan

Human-calibrated automated intelligibility evaluation of speech neuroprostheses

This paper fine-tunes an ASR model on human-transcribed synthesized speech to better align its word error rate with human perception, achieving higher correlation than zero-shot ASR.

A generalizable speech neuroprosthesis

This paper introduces a multi-user transformer-based decoder for intracortical speech BCIs, achieving lower word error rates with less training data than individual models.

Brain2voice 2.0: High-performance voice synthesis brain-computer interface

Brain2voice 2.0 improves voice synthesis from neural signals, achieving 5.24% word error rate, 8x better than prior methods, enabling real-time intelligible speech for paralyzed individuals.

Encoding of speech modes and loudness in ventral precentral gyrus

This study decodes speech mode and loudness from ventral precentral gyrus activity in two participants, achieving high accuracy in predicting speech parameters and developing a closed-loop decoder for expressive speech neuroprostheses.

Putting computational models of immunity to the test - an invited challenge to predict B. pertussis vaccination outcomes

The paper benchmarks 49 algorithms for predicting B. pertussis vaccination outcomes, finding that purpose-built models outperform literature-based ones due to better handling of nonlinearities and data preprocessing.