Amit Ranjan Trivedi

Low Power Speaker Identification using Look Up-free Gaussian Mixture Model in CMOS

2019

This work discusses a CMOS-based implementation of low power speaker identification (SI) using Gaussian mixture models (GMMs). Conventionally, GMM-based SI relies on repeated access to log-add look-up table (LUT). With increasing dimensional of speaker models …

Towards Model-Size Agnostic, Compute-Free, Memorization-based Inference of Deep Learning

2024

The rapid advancement of deep neural networks has significantly improved various tasks, such as image and speech recognition. However, as the complexity of these models increases, so does the computational cost and the number of …

Neural Precision Polarization: Simplifying Neural Network Inference with Dual-Level Precision

2025

We introduce a precision polarization scheme for DNN inference that utilizes only very low and very high precision levels, assigning low precision to the majority of network weights and activations while reserving high precision paths …