研究実績の概要 |
Under the real-life condition, people often need to express their emotions with appropriate speech in the noisy environments. In the past year, we mainly explored to reduce misperceptions of the emotional content of speech in the noisy environments. We found that VQ-VAE-based speech waveforms typically have inappropriate prosodic structure. Thus we introduced an important extension to VQ-VAE for learning F0-related suprasegmental information simultaneously along with phone features. We have published a conference paper on this work. We have tried to convert the emotional speech in the clean environment to the emotional speech with Lombard effect under the VQVAE. We have also investigated various adversarial networks to improve the emotional intelligibility of the decoded speech.
|