Facetron: A Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations
This work addresses the challenge of multi-speaker face-to-speech synthesis, which could benefit applications in assistive technologies or multimedia, but it appears incremental as it builds on existing cross-modal and GAN-based methods.
The paper tackles the problem of generating speech waveforms from face images for multiple speakers, including unseen ones, by using a GAN with independently controlled linguistic and speaker features, achieving superior performance in objective and subjective evaluations such as speech recognition accuracy and naturalness scores.
In this paper, we propose a multi-speaker face-to-speech waveform generation model that also works for unseen speaker conditions. Using a generative adversarial network (GAN) with linguistic and speaker characteristic features as auxiliary conditions, our method directly converts face images into speech waveforms under an end-to-end training framework. The linguistic features are extracted from lip movements using a lip-reading model, and the speaker characteristic features are predicted from face images using cross-modal learning with a pre-trained acoustic model. Since these two features are uncorrelated and controlled independently, we can flexibly synthesize speech waveforms whose speaker characteristics vary depending on the input face images. We show the superiority of our proposed model over conventional methods in terms of objective and subjective evaluation results. Specifically, we evaluate the performances of linguistic features by measuring their accuracy on an automatic speech recognition task. In addition, we estimate speaker and gender similarity for multi-speaker and unseen conditions, respectively. We also evaluate the aturalness of the synthesized speech waveforms using a mean opinion score (MOS) test and non-intrusive objective speech quality assessment (NISQA).The demo samples of the proposed and other models are available at https://sam-0927.github.io/