paper-with-me

홈 › Papers

StarGAN-VC+ASR: StarGAN-based Non-Parallel Voice Conversion Regularized by Automatic Speech Recognition

2021-08-10 · Shoki Sakamoto, Akira Taniguchi, Tadahiro Taniguchi, Hirokazu Kameoka

Preserving the linguistic content of input speech is essential during voice conversion (VC). 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 method is powerful, it can fail to preserve the linguistic content of input speech when the number of available training samples is extremely small. To overcome this problem, we propose the use of automatic speech recognition to assist model training, to improve StarGAN-VC, especially in low-resource scenarios. Experimental results show that using our proposed method, StarGAN-VC can retain more linguistic information than vanilla StarGAN-VC.

📄 PDF Abstract BibTeX arXiv:2108.04395

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Generative Adversarial Networkspeech-recognitionSpeech RecognitionVoice Conversion

Similar Papers 제목 키워드 기반

StarGAN-ZSVC: Towards Zero-Shot Voice Conversion in Low-Resource Contexts

2021-05-31 · Matthew Baas, Herman Kamper

Voice conversion is the task of converting a spoken utterance from a source speaker so that it appears to be said by a different target speaker while retaining the linguistic content of the utterance. Recent advances hav…

Voice Conversion

Nonparallel Voice Conversion with Augmented Classifier Star Generative Adversarial Networks

2020-08-27 · Hirokazu Kameoka, Takuhiro Kaneko, Kou Tanaka, Nobukatsu Hojo

We previously proposed a method that allows for nonparallel voice conversion (VC) by using a variant of generative adversarial networks (GANs) called StarGAN. The main features of our method, called StarGAN-VC, are as fo…

Voice Conversion

Boosting Star-GANs for Voice Conversion with Contrastive Discriminator

2022-09-21 · Shijing Si, Jianzong Wang, xulong Zhang, Xiaoyang Qu 외

Nonparallel multi-domain voice conversion methods such as the StarGAN-VCs have been widely applied in many scenarios. However, the training of these models usually poses a challenge due to their complicated adversarial n…

Contrastive LearningVoice Conversion

StarGAN-based Emotional Voice Conversion for Japanese Phrases

2021-04-05 · Asuka Moritani, Ryo Ozaki, Shoki Sakamoto, Hirokazu Kameoka 외

This paper shows that StarGAN-VC, a spectral envelope transformation method for non-parallel many-to-many voice conversion (VC), is capable of emotional VC (EVC). Although StarGAN-VC has been shown to enable speaker iden…

Voice Conversion

StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion

2019-07-29 · Takuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka, Nobukatsu Hojo

Non-parallel multi-domain voice conversion (VC) is a technique for learning mappings among multiple domains without relying on parallel data. This is important but challenging owing to the requirement of learning multipl…

Voice Conversion