Towards Realistic Emotional Voice Conversion Using Controllable Emotional Intensity
2024 · Tianhua Qi, Shiyan Wang, Cheng Lu, et al.
Abstract
Realistic emotional voice conversion (EVC) aims to enhance emotional diversity of converted audios, making the synthesized voices more authentic and natural. To this end, we propose Emotional Intensity-aware Network (EINet), dynamically adjusting intonation and rhythm by incorporating controllable emotional intensity. To better capture nuances in emotional intensity, we go beyond mere distance measurements among acoustic features. Instead, an emotion evaluator is utilized to precisely quantify speaker's emotional state. By employing an intensity mapper, intensity pseudo-labels are obtained to bridge the gap between emotional speech intensity modeling and run-time conversion. To ensure high speech quality while retaining controllability, an emotion renderer is used for combining linguistic features smoothly with manipulated emotional features at frame level. Furthermore, we employ a duration predictor to facilitate adaptive prediction of rhythm changes condition on specifying intensity
Authors
(none)
Tags
Stats
Related papers
- Mixed-evc: Mixed Emotion Synthesis And Control In Voice Conversion (2022)4.52
- Emoreg: Directional Latent Vector Modeling For Emotional Intensity Regularization In Diffusion-based Voice Conversion (2024)2.26
- Limited Data Emotional Voice Conversion Leveraging Text-to-speech: Two-stage Sequence-to-sequence Training (2021)10.35
- An Overview & Analysis Of Sequence-to-sequence Emotional Voice Conversion (2022)8.60
- PAVITS: Exploring Prosody-aware VITS For End-to-end Emotional Voice Conversion (2024)8.35
- An Improved Stargan For Emotional Voice Conversion: Enhancing Voice Quality And Data Augmentation (2021)7.81
- Attention-based Interactive Disentangling Network For Instance-level Emotional Voice Conversion (2023)6.34
- ZSDEVC: Zero-shot Diffusion-based Emotional Voice Conversion With Disentangled Mechanism (2024)0.00