Search Results for author: Shrikanth. S. Narayanan

Found 3 papers, 0 papers with code

Normalization Before Shaking Toward Learning Symmetrically Distributed Representation Without Margin in Speech Emotion Recognition

no code implementations2 Aug 2018 Che-Wei Huang, Shrikanth. S. Narayanan

Regularization is crucial to the success of many practical deep learning models, in particular in a more often than not scenario where there are only a few to a moderate number of accessible training samples.

Data Augmentation General Classification +1

Characterizing Types of Convolution in Deep Convolutional Recurrent Neural Networks for Robust Speech Emotion Recognition

no code implementations7 Jun 2017 Che-Wei Huang, Shrikanth. S. Narayanan

Deep convolutional neural networks are being actively investigated in a wide range of speech and audio processing applications including speech recognition, audio event detection and computational paralinguistics, owing to their ability to reduce factors of variations, for learning from speech.

Event Detection Speech Emotion Recognition +2

Generalized Ambiguity Decomposition for Understanding Ensemble Diversity

no code implementations28 Dec 2013 Kartik Audhkhasi, Abhinav Sethy, Bhuvana Ramabhadran, Shrikanth. S. Narayanan

We present extensions of this decomposition to common regression and classification loss functions, and report a simulation-based analysis of the diversity term and the accuracy of the decomposition.

General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.