DeepAI AI Chat
Log In Sign Up

VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019

by   Andros Tjandra, et al.
Nara Institute of Science and Technology

We describe our submitted system for the ZeroSpeech Challenge 2019. The current challenge theme addresses the difficulty of constructing a speech synthesizer without any text or phonetic labels and requires a system that can (1) discover subword units in an unsupervised way, and (2) synthesize the speech with a target speaker's voice. Moreover, the system should also balance the discrimination score ABX, the bit-rate compression rate, and the naturalness and the intelligibility of the constructed voice. To tackle these problems and achieve the best trade-off, we utilize a vector quantized variational autoencoder (VQ-VAE) and a multi-scale codebook-to-spectrogram (Code2Spec) inverter trained by mean square error and adversarial loss. The VQ-VAE extracts the speech to a latent space, forces itself to map it into the nearest codebook and produces compressed representation. Next, the inverter generates a magnitude spectrogram to the target voice, given the codebook vectors from VQ-VAE. In our experiments, we also investigated several other clustering algorithms, including K-Means and GMM, and compared them with the VQ-VAE result on ABX scores and bit rates. Our proposed approach significantly improved the intelligibility (in CER), the MOS, and discrimination ABX scores compared to the official ZeroSpeech 2019 baseline or even the topline.


page 1

page 2

page 3

page 4


Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge

In this paper, we report our submitted system for the ZeroSpeech 2020 ch...

Vector-quantized neural networks for acoustic unit discovery in the ZeroSpeech 2020 challenge

In this paper, we explore vector quantization for acoustic unit discover...

The Zero Resource Speech Challenge 2019: TTS without T

We present the Zero Resource Speech Challenge 2019, which proposes to bu...

Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks

For our submission to the ZeroSpeech 2019 challenge, we apply discrete l...

KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms

In this paper, we propose a novel neural network model called KaraSinger...

Improved Prosody from Learned F0 Codebook Representations for VQ-VAE Speech Waveform Reconstruction

Vector Quantized Variational AutoEncoders (VQ-VAE) are a powerful repres...