Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Multi-Conditioning & Data Augmentation using Generative Noise Model for Speech Emotion Recognition in Noisy Conditions

Abstract: 

Degradation due to additive noise is a significant road block in the real-life deployment of Speech Emotion Recognition (SER) systems. Most of the previous work in this field dealt with the noise degradation either at the signal or at the feature level. In this paper, to address the robustness aspect of the SER in additive noise scenarios, we propose multi-conditioning and data augmentation using an utterance level parametric generative noise model. The generative noise model is designed to generate noise types which can span the entire noise space in the mel-filterbank energy domain. This characteristic of the model renders the system robust against unseen noise conditions. The generated noise types can be used to create multi-conditioned data for training the SER systems. Multi-conditioning approach can also be used to increase the training data by many folds where such data is limited. We report the performance of the proposed method on two datasets, namely EmoDB and IEMOCAP. We also explore multi-conditioning and data augmentation using noise samples from NOISEX-92 noise database.

up
0 users have voted:

Paper Details

Authors:
Upasana Tiwari, Meet Soni, Rupayan Chakraborty, Ashish Panda, Sunil Kumar Kopparapu
Submitted On:
20 May 2020 - 5:01am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Upasana Tiwari
Paper Code:
5701
Document Year:
2020
Cite

Document Files

ICASSP2020_ppt_5701.pdf

(27)

Keywords

Additional Categories

Subscribe

[1] Upasana Tiwari, Meet Soni, Rupayan Chakraborty, Ashish Panda, Sunil Kumar Kopparapu, "Multi-Conditioning & Data Augmentation using Generative Noise Model for Speech Emotion Recognition in Noisy Conditions", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5403. Accessed: Aug. 05, 2020.
@article{5403-20,
url = {http://sigport.org/5403},
author = {Upasana Tiwari; Meet Soni; Rupayan Chakraborty; Ashish Panda; Sunil Kumar Kopparapu },
publisher = {IEEE SigPort},
title = {Multi-Conditioning & Data Augmentation using Generative Noise Model for Speech Emotion Recognition in Noisy Conditions},
year = {2020} }
TY - EJOUR
T1 - Multi-Conditioning & Data Augmentation using Generative Noise Model for Speech Emotion Recognition in Noisy Conditions
AU - Upasana Tiwari; Meet Soni; Rupayan Chakraborty; Ashish Panda; Sunil Kumar Kopparapu
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5403
ER -
Upasana Tiwari, Meet Soni, Rupayan Chakraborty, Ashish Panda, Sunil Kumar Kopparapu. (2020). Multi-Conditioning & Data Augmentation using Generative Noise Model for Speech Emotion Recognition in Noisy Conditions. IEEE SigPort. http://sigport.org/5403
Upasana Tiwari, Meet Soni, Rupayan Chakraborty, Ashish Panda, Sunil Kumar Kopparapu, 2020. Multi-Conditioning & Data Augmentation using Generative Noise Model for Speech Emotion Recognition in Noisy Conditions. Available at: http://sigport.org/5403.
Upasana Tiwari, Meet Soni, Rupayan Chakraborty, Ashish Panda, Sunil Kumar Kopparapu. (2020). "Multi-Conditioning & Data Augmentation using Generative Noise Model for Speech Emotion Recognition in Noisy Conditions." Web.
1. Upasana Tiwari, Meet Soni, Rupayan Chakraborty, Ashish Panda, Sunil Kumar Kopparapu. Multi-Conditioning & Data Augmentation using Generative Noise Model for Speech Emotion Recognition in Noisy Conditions [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5403