Log In Sign Up

Improving Accent Conversion with Reference Encoder and End-To-End Text-To-Speech

by   Wenjie Li, et al.

Accent conversion (AC) transforms a non-native speaker's accent into a native accent while maintaining the speaker's voice timbre. In this paper, we propose approaches to improving accent conversion applicability, as well as quality. First of all, we assume no reference speech is available at the conversion stage, and hence we employ an end-to-end text-to-speech system that is trained on native speech to generate native reference speech. To improve the quality and accent of the converted speech, we introduce reference encoders which make us capable of utilizing multi-source information. This is motivated by acoustic features extracted from native reference and linguistic information, which are complementary to conventional phonetic posteriorgrams (PPGs), so they can be concatenated as features to improve a baseline system based only on PPGs. Moreover, we optimize model architecture using GMM-based attention instead of windowed attention to elevate synthesized performance. Experimental results indicate when the proposed techniques are applied the integrated system significantly raises the scores of acoustic quality (30% relative increase in mean opinion score) and native accent (68% relative preference) while retaining the voice identity of the non-native speaker.


page 1

page 2

page 3

page 4


End-to-End Voice Conversion with Information Perturbation

The ideal goal of voice conversion is to convert the source speaker's sp...

Cross-lingual Text-To-Speech with Flow-based Voice Conversion for Improved Pronunciation

This paper presents a method for end-to-end cross-lingual text-to-speech...

Space-efficient RLZ-to-LZ77 conversion

Consider a text T [1..n] prefixed by a reference sequence R = T [1..ℓ]. ...

Voice-preserving Zero-shot Multiple Accent Conversion

Most people who have tried to learn a foreign language would have experi...

A Preliminary Study of a Two-Stage Paradigm for Preserving Speaker Identity in Dysarthric Voice Conversion

We propose a new paradigm for maintaining speaker identity in dysarthric...

The NTU-AISG Text-to-speech System for Blizzard Challenge 2020

We report our NTU-AISG Text-to-speech (TTS) entry systems for the Blizza...

SVSNet: An End-to-end Speaker Voice Similarity Assessment Model

Neural evaluation metrics derived for numerous speech generation tasks h...