DQR-TTS: Semi-supervised Text-to-speech Synthesis with Dynamic Quantized Representation

Pipeline of the proposed method

Abstract

Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this paper, we introduce a novel semi-supervised text-to-speech synthesis model that learns from both paired and unpaired data to address this challenge. The key component of the proposed model is a dynamic quantized representation module, which is integrated into a sequential autoencoder. When given paired data, the module incorporates a trainable codebook that learns quantized representations under the supervision of the paired data. However, due to the limited paired data in low-resource scenario, these paired data are difficult to cover all phonemes. Then unpaired data is fed to expand the dynamic codebook by adding quantized representation vectors that are sufficiently distant from the existing ones during training. Experiments show that with less than 120 minutes of paired data, the proposed method outperforms existing methods in both subjective and objective metrics.

Type
Publication
In The 13th IEEE International Conference on Big Data and Cloud Computing
Click the Cite button above to demo the feature to enable visitors to import publication metadata into their reference management software.
Pengcheng Li
Pengcheng Li
University of Science and Technology of China
Ning Cheng
Ning Cheng
Director