A Vector Quantized Variational Autoencoder (VQ-VAE) Autoregressive Neural F0 Model for Statistical Parametric Speech Synthesis

You are here

Top Reasons to Join SPS Today!

1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.

A Vector Quantized Variational Autoencoder (VQ-VAE) Autoregressive Neural F0 Model for Statistical Parametric Speech Synthesis

By: 
Xin Wang; Shinji Takaki; Junichi Yamagishi; Simon King; Keiichi Tokuda

Recurrent neural networks (RNNs) can predict fundamental frequency (F 0 ) for statistical parametric speech synthesis systems, given linguistic features as input. However, these models assume conditional independence between consecutive F 0 values, given the RNN state. In a previous study, we proposed autoregressive (AR) neural F 0 models to capture the causal dependency of successive F 0 values. In subjective evaluations, a deep AR model (DAR) outperformed an RNN. Here, we propose a Vector Quantized Variational Autoencoder (VQ-VAE) neural F 0 model that is both more efficient and more interpretable than the DAR. This model has two stages: one uses the VQ-VAE framework to learn a latent code for the F 0 contour of each linguistic unit, and other learns to map from linguistic features to latent codes. In contrast to the DAR and RNN, which process the input linguistic features frame-by-frame, the new model converts one linguistic feature vector into one latent code for each linguistic unit. The new model achieves better objective scores than the DAR, has a smaller memory footprint and is computationally faster. Visualization of the latent codes for phones and moras reveals that each latent code represents an F 0 shape for a linguistic unit.

SPS on Twitter

  • Share SPS membership with your students, colleagues, and friends! Celebrate - Students and Professionals… https://t.co/qXNA12wxQ6
  • DEADLINE APPROACHING: The IEEE Transactions on Multimedia is accepting submissions for a Special Issue on Learning… https://t.co/XHR6eqwR1p
  • Celebrate now through 27 February! Get a 50% discount on SPS membership – offers available for Student a… https://t.co/enKoDMwiek
  • The SPACE Webinar Series continues Tuesday, 23 February at 10:00 AM EST when Dr. Pier Luigi Dragotti presents "Comp… https://t.co/FcZaAiHzZE
  • The Brain Space Initiative Talk Series continues on Friday, 26 February at 11:00 AM EST when Dr. Emmanuelle Tognoli… https://t.co/PTMXdSGpMa

SPS Videos


Signal Processing in Home Assistants

 


Multimedia Forensics


Careers in Signal Processing             

 


Under the Radar