2 citations · 4 across the 2 of their papers we have counts for
Showing eess.ASShow all
2 papers · 1 filter
eess.AS2021★ 2 cited
UniTTS: Residual Learning of Unified Embedding Space for Speech Style Control
Minsu Kang, Sungjae Kim, Injung Kim
We propose a novel high-fidelity expressive speech synthesis model, UniTTS, that learns and controls overlapping style attributes avoiding interference. UniTTS represents multiple…
eess.AS2021★ 2 cited
Fast DCTTS: Efficient Deep Convolutional Text-to-Speech
Minsu Kang, Jihyun Lee, Simin Kim +1
We propose an end-to-end speech synthesizer, Fast DCTTS, that synthesizes speech in real time on a single CPU thread. The proposed model is composed of a carefully-tuned lightweigh…