Aug 10, 2021 · We propose the use of automatic speech recognition to assist model training, to improve StarGAN-VC, especially in low-resource scenarios.
This work proposes the use of automatic speech recognition to assist model training, to improve StarGAN-VC, especially in low-resource scenarios, ...
Similar to the PPG-based approach, the method proposed in this paper improves the ability of StarGAN-VC to preserve the lin- guistic content of input speech by ...
The star generative adversarial network-based VC method (StarGAN-VC) is a recently developed method that allows non-parallel many-to-many VC. Although this ...
StarGAN-VC+ASR: StarGAN-Based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition. August 2021. DOI:10.21437/Interspeech.2021-492.
The star generative adversarial network-based VC method (StarGAN-VC) is a recently developed method that allows non-parallel many-to-many VC.
This repository provides an official PyTorch implementation for StarGAN-VC. StarGAN-VC is a nonparallel many-to-many voice conversion (VC) method using star ...
Missing: ASR: Based Regularized Automatic
People also ask
What is ASR speech recognition?
Is ASR the same as speech-to-text?
What is the difference between speech recognition and automatic speech recognition?
What is automated voice recognition?
Abstract. This paper proposes a method that allows non-parallel many-to-many voice conversion (VC) by using a variant of a generative adversarial network ...
This paper proposes a method that allows non-parallel many-to-many voice conversion (VC) by using a variant of a generative adversarial network (GAN) called ...
Kameoka, “StarGAN-VC+ ASR: Stargan-based non-parallel voice conversion regularized by automatic speech recognition,” arXiv preprint arXiv:2108.04395, 2021.