A Multi-Discriminator CycleGAN for Unsupervised Non-Parallel Speech Domain Adaptation
share
Domain adaptation plays an important role for speech recognition models, in particular, for domains that have low resources. We propose a novel generative model based on cyclic-consistent generative adversarial network (CycleGAN) for unsupervised non-parallel speech domain adaptation. The proposed model employs multiple independent discriminator on the power spectrogram, each in charge of different frequency bands. As a result we have 1) better discriminators that focuses on fine-grained details of the frequency features, and 2) a generator that is capable of generating more realistic domain adapted spectrogram. We demonstrate the effectiveness of our method on speech recognition with gender adaptation, where the model only have access to supervised data from one gender during training, but is evaluated on the other at testing time. Our model is able to achieve an average of 7.41% on phoneme error rate, and 11.10% word error rate relative performance improvement as compared to the baseline on TIMIT and WSJ dataset, respectively. Qualitatively, our model also generate more realistic sounding speech synthesis when conditioned on data from the other domain.
READ FULL TEXT