Generative Adversarial Networks for Singing Voice Conversion with and without Parallel Data - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Berrak Sisman, Haizhou Li 0001. Generative Adversarial Networks for Singing Voice Conversion with and without Parallel Data. In Kong-Aik Lee, Takafumi Koshinaka, Koichi Shinoda, editors, Odyssey 2020: The Speaker and Language Recognition Workshop, 1-5 November 2020, Tokyo, Japan. pages 238-244, ISCA, 2020. [doi]

The following publications are possibly variants of this publication:

SINGAN: Singing Voice Conversion with Generative Adversarial NetworksBerrak Sisman, Karthika Vijayan, Minghui Dong, Haizhou Li 0001. apsipa 2019: 112-118 [doi]

Pitchnet: Unsupervised Singing Voice Conversion with Pitch Adversarial NetworkChengqi Deng, Chengzhu Yu, Heng Lu, Chao Weng, Dong Yu 0001. icassp 2020: 7749-7753 [doi]

runs on WebDSL