Paper ID | SPE-49.4 | ||
Paper Title | LEARNING DISENTANGLED PHONE AND SPEAKER REPRESENTATIONS IN A SEMI-SUPERVISED VQ-VAE PARADIGM | ||
Authors | Jennifer Williams, University of Edinburgh, United Kingdom; Zhao Yi, Erica Cooper, Junichi Yamagishi, National Institute for Informatics, Japan | ||
Session | SPE-49: Speech Synthesis 7: General Topics | ||
Location | Gather.Town | ||
Session Time: | Friday, 11 June, 11:30 - 12:15 | ||
Presentation Time: | Friday, 11 June, 11:30 - 12:15 | ||
Presentation | Poster | ||
Topic | Speech Processing: [SPE-SYNT] Speech Synthesis and Generation | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | We present a new approach to disentangle speaker voice and phone content by introducing new components to the VQ-VAE architecture for speech synthesis. The original VQ-VAE does not generalize well to unseen speakers or content. To alleviate this problem, we have incorporated a speaker encoder and speaker VQ codebook that learns global speaker characteristics entirely separate from the existing sub-phone codebooks. We also compare two training methods: self-supervised with global conditions and semi-supervised with speaker labels. Adding a speaker VQ component improves objective measures of speech synthesis quality (estimated MOS, speaker similarity, ASR-based intelligibility) and provides learned representations that are meaningful. Our speaker VQ codebook indices can be used in a simple speaker diarization task and perform slightly better than an x-vector baseline. Additionally, phones can be recognized from sub-phone VQ codebook indices in our semi-supervised VQ-VAE better than self-supervised with global conditions. |