End-to-End Text-to-Speech using Latent Duration based on VQ-VAE

October 19, 2020 Β· Declared Dead Β· πŸ› IEEE International Conference on Acoustics, Speech, and Signal Processing

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Yusuke Yasuda, Xin Wang, Junichi Yamagishi arXiv ID 2010.09602 Category eess.AS: Audio & Speech Cross-listed cs.CL, cs.SD Citations 17 Venue IEEE International Conference on Acoustics, Speech, and Signal Processing Last Checked 6 months ago
Abstract
Explicit duration modeling is a key to achieving robust and efficient alignment in text-to-speech synthesis (TTS). We propose a new TTS framework using explicit duration modeling that incorporates duration as a discrete latent variable to TTS and enables joint optimization of whole modules from scratch. We formulate our method based on conditional VQ-VAE to handle discrete duration in a variational autoencoder and provide a theoretical explanation to justify our method. In our framework, a connectionist temporal classification (CTC) -based force aligner acts as the approximate posterior, and text-to-duration works as the prior in the variational autoencoder. We evaluated our proposed method with a listening test and compared it with other TTS methods based on soft-attention or explicit duration modeling. The results showed that our systems rated between soft-attention-based methods (Transformer-TTS, Tacotron2) and explicit duration modeling-based methods (Fastspeech).
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Audio & Speech

Died the same way β€” πŸ‘» Ghosted