MaskCycleGAN-based Whisper to Normal Speech Conversion
This work addresses speech conversion for applications like assistive technology, but it is incremental as it builds on existing MaskCycleGAN methods.
The paper tackled the problem of converting whispered speech to normal speech using a MaskCycleGAN approach, achieving superior performance with objective metrics like PESQ and G-Loss on the wTIMIT dataset.
Whisper to normal speech conversion is an active area of research. Various architectures based on generative adversarial networks have been proposed in the recent past. Especially, recent study shows that MaskCycleGAN, which is a mask guided, and cyclic consistency keeping, generative adversarial network, performs really well for voice conversion from spectrogram representations. In the current work we present a MaskCycleGAN approach for the conversion of whispered speech to normal speech. We find that tuning the mask parameters, and pre-processing the signal with a voice activity detector provides superior performance when compared to the existing approach. The wTIMIT dataset is used for evaluation. Objective metrics such as PESQ and G-Loss are used to evaluate the converted speech, along with subjective evaluation using mean opinion score. The results show that the proposed approach offers considerable benefits.