Speech Synthesis with Mixed Emotions
Zhou, Kun, Sisman, Berrak, Rana, Rajib, Schuller, B. W., Li, Haizhou
–arXiv.org Artificial Intelligence
Emotional speech synthesis aims to synthesize human voices with various emotional effects. The current studies are mostly focused on imitating an averaged style belonging to a specific emotion type. In this paper, we seek to generate speech with a mixture of emotions at run-time. We propose a novel formulation that measures the relative difference between the speech samples of different emotions. We then incorporate our formulation into a sequence-to-sequence emotional text-to-speech framework. During the training, the framework does not only explicitly characterize emotion styles, but also explores the ordinal nature of emotions by quantifying the differences with other emotions. At run-time, we control the model to produce the desired emotion mixture by manually defining an emotion attribute vector. The objective and subjective evaluations have validated the effectiveness of the proposed framework. To our best knowledge, this research is the first study on modelling, synthesizing, and evaluating mixed emotions in speech.
arXiv.org Artificial Intelligence
Dec-28-2022
- Country:
- Oceania > Australia
- Queensland (0.04)
- New South Wales > Sydney (0.04)
- North America > United States
- New York (0.04)
- Texas > Dallas County
- Dallas (0.04)
- California > Los Angeles County
- Santa Monica (0.04)
- Europe
- France (0.04)
- United Kingdom > England
- Greater London > London (0.04)
- Oxfordshire > Oxford (0.04)
- Cambridgeshire > Cambridge (0.04)
- Germany
- Bremen > Bremen (0.14)
- North Rhine-Westphalia > Upper Bavaria
- Munich (0.04)
- Bavaria > Upper Bavaria
- Munich (0.04)
- Asia
- Japan (0.04)
- Singapore > Central Region
- Singapore (0.04)
- China
- Hong Kong (0.04)
- Sichuan Province > Chengdu (0.04)
- Guangdong Province
- Oceania > Australia
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Technology:
- Information Technology > Artificial Intelligence
- Vision (1.00)
- Speech > Speech Synthesis (1.00)
- Cognitive Science > Emotion (0.94)
- Machine Learning > Neural Networks
- Deep Learning (1.00)
- Information Technology > Artificial Intelligence