The Sequence-to-Sequence Baseline for the Voice Conversion Challenge 2020: Cascading ASR and TTS
This work addresses voice conversion for speech processing applications, but it is incremental as it revisits a naive approach with modern tools.
The paper tackled voice conversion by using a sequence-to-sequence framework to cascade automatic speech recognition and text-to-speech models, achieving top performance in conversion similarity in the Voice Conversion Challenge 2020.
This paper presents the sequence-to-sequence (seq2seq) baseline system for the voice conversion challenge (VCC) 2020. We consider a naive approach for voice conversion (VC), which is to first transcribe the input speech with an automatic speech recognition (ASR) model, followed using the transcriptions to generate the voice of the target with a text-to-speech (TTS) model. We revisit this method under a sequence-to-sequence (seq2seq) framework by utilizing ESPnet, an open-source end-to-end speech processing toolkit, and the many well-configured pretrained models provided by the community. Official evaluation results show that our system comes out top among the participating systems in terms of conversion similarity, demonstrating the promising ability of seq2seq models to convert speaker identity. The implementation is made open-source at: https://github.com/espnet/espnet/tree/master/egs/vcc20.