Sudarsana Reddy Kadiri

Identity leakage previously inflated Mandarin depression detection scores to 0.954, but CLeaD reveals the true performance is significantly lower, exposing critical flaws in existing methodologies.

Achieving an 8x reduction in training time without sacrificing ASR performance could revolutionize how we deploy speech recognition systems for dysarthric users.

Tailored acoustic feature selection can boost dysarthric speech recognition accuracy by over 4.6%, transforming how we approach ASR for low-resource groups.

Tailored acoustic features can boost dysarthric speech recognition performance by over 4% using advanced neural network models.

Tailored data augmentation techniques can reduce word error rates in dysarthric speech recognition by over 30%, depending on severity.

Phase information proves crucial for understanding consonant intelligibility in noise, challenging traditional views on speech processing.

The SFF-based narrowband DoA estimator not only mitigates spatial aliasing but also outperforms leading broadband methods in challenging acoustic environments.

A new multimodal dataset links brain activity, muscle activation, and articulation in speech, opening doors to understanding the causal chain of speech production.