XAI-BayesHAR: A novel Framework for Human Activity Recognition with Integrated Uncertainty and Shapely Values

no code implementations • 7 Nov 2022 • Anand Dubey, Niall Lyons, Avik Santra, Ashutosh Pandey

Human activity recognition (HAR) using IMU sensors, namely accelerometer and gyroscope, has several applications in smart homes, healthcare and human-machine interface systems.

Explainable Artificial Intelligence (XAI) Human Activity Recognition +1

Harnessing the Power of Explanations for Incremental Training: A LIME-Based Approach

no code implementations • 2 Nov 2022 • Arnab Neelim Mazumder, Niall Lyons, Ashutosh Pandey, Avik Santra, Tinoosh Mohsenin

In this work, model explanations are fed back to the feed-forward training to help the model generalize better.

Feature Importance Incremental Learning +1

Time-Domain Speech Enhancement for Robust Automatic Speech Recognition

no code implementations • 24 Oct 2022 • Yufeng Yang, Ashutosh Pandey, DeLiang Wang

However, speech enhancement has not been established as an effective frontend for robust automatic speech recognition (ASR) in noisy conditions compared to an ASR model trained on noisy speech directly.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Dense CNN with Self-Attention for Time-Domain Speech Enhancement

no code implementations • 3 Sep 2020 • Ashutosh Pandey, DeLiang Wang

Even though the proposed loss is based on magnitudes only, a constraint imposed by noise prediction ensures that the loss enhances both magnitude and phase.

Speech Enhancement