Litcius/Paper detail

Stargan for Emotional Speech Conversion: Validated by Data Augmentation of End-To-End Emotion Recognition

Georgios Rizos, Alice Baird, Max Elliott, Björn W. Schuller

2020109 citationsDOIOpen Access PDF

Abstract

In this paper, we propose an adversarial network implementation for speech emotion conversion as a data augmentation method, validated by a multi-class speech affect recognition task. In our setting, we do not assume the availability of parallel data, and we additionally make it a priority to exploit as much as possible the available training data by adopting a cycle-consistent, class-conditional generative adversarial network with an auxiliary domain classifier. Our generated samples are valuable for data augmentation, achieving a corresponding 2% and 6% absolute increase in Micro- and MacroF1 compared to the baseline in a 3-class classification paradigm using a deep, end-to-end network. We finally perform a human perception evaluation of the samples, through which we conclude that our samples are indicative of their target emotion, albeit showing a tendency for confusion in cases where the emotional attribute of valence and arousal are inconsistent.

Topics & Concepts

Computer scienceEnd-to-end principleClassifier (UML)Adversarial systemSpeech recognitionEmotion recognitionConfusionGenerative adversarial networkGenerative grammarArtificial intelligenceValence (chemistry)Emotion classificationExploitPerceptionDeep learningPsychologyComputer securityPsychoanalysisPhysicsNeuroscienceQuantum mechanicsSpeech and Audio ProcessingMusic and Audio ProcessingSpeech Recognition and Synthesis
Stargan for Emotional Speech Conversion: Validated by Data Augmentation of End-To-End Emotion Recognition | Litcius