1 citations · 1 across the 4 of their papers we have counts for
Showing eess.ASShow all
2 papers · 1 filter
eess.AS2023★ 1 cited
Speak While You Think: Streaming Speech Synthesis During Text Generation
Avihu Dekel, Slava Shechtman, Raul Fernandez +3
Large Language Models (LLMs) demonstrate impressive capabilities, yet interaction with these models is mostly facilitated through text. Using Text-To-Speech to synthesize LLM outpu…
eess.AS2022
Transplantation of Conversational Speaking Style with Interjections in Sequence-to-Sequence Speech Synthesis
Raul Fernandez, David Haws, Guy Lorberbom +2
Sequence-to-Sequence Text-to-Speech architectures that directly generate low level acoustic features from phonetic sequences are known to produce natural and expressive speech when…