CNEG-VC: Contrastive Learning Using Hard Negative Example In Non-Parallel Voice Conversion

Bima Prihasto, Yi-Xing Lin, Phuong Thi Le, Chien-Lin Huang, Jia-Ching Wang

Abstract: Contrastive learning has advantages for non-parallel voice conversion, but the previous conversion results could be better and more preserved. In previous techniques, negative samples were randomly selected in the features vector from different locations. A positive example could not be effectively pushed toward the query examples. We present contrastive learning in non-parallel voice conversion to solve this problem using hard negative examples. We named it CNEG-VC. Specifically, we teach the generator to generate negative examples. Our proposed generator has specific features. First, Instance-wise negative examples are generated based on voice input. Second, when taught with an adversarial loss, it can produce hard negative examples. The generator significantly improves non-parallel voice conversion performance. Our CNEG-VC achieved state-of-the-art results by outperforming previous techniques.