Improving ASR Robustness to Perturbed Speech Using Cycle-consistent Generative Adversarial Networks

Naturally introduced perturbations in audio signal, caused by emotional and physical states of the speaker, can significantly degrade the performance of Automatic Speech Recognition (ASR) systems. In this paper, we propose a front-end based on Cycle-Consistent Generative Adversarial Network (CycleGA...

Full description

Saved in:
Bibliographic Details
Main Authors: Dumpala, Sri Harsha, Sheikh, Imran, Chakraborty, Rupayan, Kopparapu, Sunil Kumar
Format: Conference Proceeding
Language:English
Subjects:
automatic speech recognition
Convolution
creaky speech
Cycle-consistent GAN
Error analysis
Feature extraction
Gallium nitride
Generators
Iron
laughter speech
Perturbation methods
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Naturally introduced perturbations in audio signal, caused by emotional and physical states of the speaker, can significantly degrade the performance of Automatic Speech Recognition (ASR) systems. In this paper, we propose a front-end based on Cycle-Consistent Generative Adversarial Network (CycleGAN) which transforms naturally perturbed speech into normal speech, and hence improves the robustness of an ASR system. The CycleGAN model is trained on non-parallel examples of perturbed and normal speech. Experiments on spontaneous laughter-speech and creaky voice datasets show that the performance of four different ASR systems improve by using speech obtained from CycleGAN based front-end, as compared to directly using the original perturbed speech. Visualization of the features of the laughter perturbed speech and those generated by the proposed front-end further demonstrates the effectiveness of our approach.
ISSN:2379-190X
DOI:10.1109/ICASSP.2019.8683793