Nonparallel Emotional Voice Conversion For Unseen Speaker-Emotion Pairs Using Dual Domain Adversarial Network & Virtual Domain Pairing
This addresses the limitation in emotional voice conversion systems that typically only handle seen speaker-emotion combinations, offering a solution for more flexible and practical applications in speech processing.
The paper tackled the problem of emotional voice conversion for unseen speaker-emotion pairs, where only neutral data is available during training and testing, and achieved this by extending StartGANv2-VC with dual encoders and a Virtual Domain Pairing strategy, evaluated on a Hindi emotional database.
Primary goal of an emotional voice conversion (EVC) system is to convert the emotion of a given speech signal from one style to another style without modifying the linguistic content of the signal. Most of the state-of-the-art approaches convert emotions for seen speaker-emotion combinations only. In this paper, we tackle the problem of converting the emotion of speakers whose only neutral data are present during the time of training and testing (i.e., unseen speaker-emotion combinations). To this end, we extend a recently proposed StartGANv2-VC architecture by utilizing dual encoders for learning the speaker and emotion style embeddings separately along with dual domain source classifiers. For achieving the conversion to unseen speaker-emotion combinations, we propose a Virtual Domain Pairing (VDP) training strategy, which virtually incorporates the speaker-emotion pairs that are not present in the real data without compromising the min-max game of a discriminator and generator in adversarial training. We evaluate the proposed method using a Hindi emotional database.