Accurate Emotion Strength Assessment For Seen And Unseen Speech Based On Data-driven Deep Learning
2022 · Rui Liu, Berrak Sisman, Björn Schuller, et al.
Abstract
Emotion classification of speech and assessment of the emotion strength are required in applications such as emotional text-to-speech and voice conversion. The emotion attribute ranking function based on Support Vector Machine (SVM) was proposed to predict emotion strength for emotional speech corpus. However, the trained ranking function doesn't generalize to new domains, which limits the scope of applications, especially for out-of-domain or unseen speech. In this paper, we propose a data-driven deep learning model, i.e. StrengthNet, to improve the generalization of emotion strength assessment for seen and unseen speech. This is achieved by the fusion of emotional data from various domains. We follow a multi-task learning network architecture that includes an acoustic encoder, a strength predictor, and an auxiliary emotion predictor. Experiments show that the predicted emotion strength of the proposed StrengthNet is highly correlated with ground truth scores for both seen and unseen
Authors
(none)
Tags
Stats
Related papers
- Strengthnet: Deep Learning-based Emotion Strength Assessment For Emotional Speech Synthesis (2021)3.85
- Fine-grained Emotion Strength Transfer, Control And Prediction For Emotional Speech Synthesis (2020)12.25
- Attention Based Fully Convolutional Network For Speech Emotion Recognition (2018)15.25
- Pre-trained Model Representations And Their Robustness Against Noise For Speech Emotion Analysis (2023)0.00
- Two-stage Dimensional Emotion Recognition By Fusing Predictions Of Acoustic And Text Networks Using SVM (2022)12.10
- Speech Emotion Recognition With Multiscale Area Attention And Data Augmentation (2021)13.65
- Speech Emotion: Investigating Model Representations, Multi-task Learning And Knowledge Distillation (2022)6.34
- Transfer Learning For Improving Speech Emotion Classification Accuracy (2018)15.10