Multi-speaker Emotion Conversion Via Latent Variable Regularization And A Chained Encoder-decoder-predictor Network
2020 · Ravi Shankar, Hsi-Wei Hsieh, Nicolas Charon, et al.
Abstract
We propose a novel method for emotion conversion in speech based on a chained encoder-decoder-predictor neural network architecture. The encoder constructs a latent embedding of the fundamental frequency (F0) contour and the spectrum, which we regularize using the Large Diffeomorphic Metric Mapping (LDDMM) registration framework. The decoder uses this embedding to predict the modified F0 contour in a target emotional class. Finally, the predictor uses the original spectrum and the modified F0 contour to generate a corresponding target spectrum. Our joint objective function simultaneously optimizes the parameters of three model blocks. We show that our method outperforms the existing state-of-the-art approaches on both, the saliency of emotion conversion and the quality of resynthesized speech. In addition, the LDDMM regularization allows our model to convert phrases that were not present in training, thus providing evidence for out-of-sample generalization.
Authors
(none)
Tags
Stats
Related papers
- Non-parallel Emotion Conversion Using A Deep-generative Hybrid Network And An Adversarial Pair Discriminator (2020)6.77
- Nonparallel Emotional Speech Conversion (2018)11.08
- Textless Speech Emotion Conversion Using Discrete And Decomposed Representations (2021)10.74
- In-the-wild Speech Emotion Conversion Using Disentangled Self-supervised Representations And Neural Vocoder-based Resynthesis (2023)0.00
- Converting Anyone's Emotion: Towards Speaker-independent Emotional Voice Conversion (2020)11.39
- Multistage Linguistic Conditioning Of Convolutional Layers For Speech Emotion Recognition (2021)9.23
- A Diffeomorphic Flow-based Variational Framework For Multi-speaker Emotion Conversion (2022)2.26
- Seen And Unseen Emotional Style Transfer For Voice Conversion With A New Emotional Speech Dataset (2020)16.34