Voice Conversion by Cascading Automatic Speech Recognition and Text-to-Speech Synthesis with Prosody Transfer
This addresses voice conversion for speech synthesis applications, but it is incremental as it builds on existing ASR and TTS techniques with prosody transfer.
The paper tackled voice conversion by cascading ASR and TTS systems, achieving the best naturalness and similarity in the Voice Conversion Challenge 2020 mono-lingual task.
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.