Deepak Kadetotad — accepted AI-conference papers

2025

Quality and Complexity Tradeoffs for DNN-Based Binaural Speech Enhancement in Hearing Aids

Parth Mishra, Deepak Kadetotad, Eric A. Durant, Terence Betlehem, Martin F. McKinney

ICASSP 2025accepted

This paper investigates the impact of input feature frequency resolution and hyperparameter choices on deep neural network based binaural speech enhancement (SE) for hearing aids. We analyze how time-frequency resolution parameters, such as window length and hop ratio, influence speech intelligibili…

Cited by 0 Source ↗Scholar ↗

2019

Joint Optimization of Quantization and Structured Sparsity for Compressed Deep Neural Networks

Gaurav Srivastava, Deepak Kadetotad, Shihui Yin, Visar Berisha, Chaitali Chakrabarti, Jae-sun Seo

ICASSP 2019accepted

The usage of Deep Neural Networks (DNN) on resource-constrained edge devices has been limited due to their high computation and large memory requirement. In this work, we propose an algorithm to compress DNNs by jointly optimizing structured sparsity and quantization constraints in a single DNN trai…

Cited by 0 Source ↗Scholar ↗