no code implementations • 14 Nov 2022 • Perry Lam, Huayun Zhang, Nancy F. Chen, Berrak Sisman, Dorien Herremans
Text-to-speech (TTS) models have achieved remarkable naturalness in recent years, yet like most deep neural models, they have more parameters than necessary.
no code implementations • 22 Sep 2022 • Perry Lam, Huayun Zhang, Nancy F. Chen, Berrak Sisman
In this work, we seek to answer the question: what are the characteristics of selected sparse techniques on the performance and model complexity?