Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody Transfer

TL;DR

This paper introduces a voice conversion method combining ASR and TTS with prosody transfer, achieving high naturalness and speaker similarity by transferring prosody features during synthesis.

Contribution

It proposes a novel prosody transfer approach using a prosody encoder in a cascading ASR-TTS system for improved voice conversion quality.

Findings

Achieved top naturalness and similarity in Voice Conversion Challenge 2020

Demonstrated effective prosody transfer improves voice conversion

Validated the method's effectiveness through experiments

Abstract

With the development of automatic speech recognition (ASR) and text-to-speech synthesis (TTS) technique, it's intuitive to construct a voice conversion system by cascading an ASR and TTS system. In this paper, we present a ASR-TTS method for voice conversion, which used iFLYTEK ASR engine to transcribe the source speech into text and a Transformer TTS model with WaveNet vocoder to synthesize the converted speech from the decoded text. For the TTS model, we proposed to use a prosody code to describe the prosody information other than text and speaker information contained in speech. A prosody encoder is used to extract the prosody code. During conversion, the source prosody is transferred to converted speech by conditioning the Transformer TTS model with its code. Experiments were conducted to demonstrate the effectiveness of our proposed method. Our system also obtained the best naturalness and similarity in the mono-lingual task of Voice Conversion Challenge 2020.