32 citations · 68 across the 7 of their papers we have counts for
3 papers · 1 filter
Using a Pitch-Synchronous Residual Codebook for Hybrid HMM/Frame Selection Speech Synthesis
Thomas Drugman, Alexis Moinet, Thierry Dutoit +1
This paper proposes a method to improve the quality delivered by statistical parametric speech synthesizers. For this, we use a codebook of pitch-synchronous residual frames, so as…
Singing Synthesis: with a little help from my attention
Orazio Angelini, Alexis Moinet, Kayoko Yanagisawa +1
We present UTACO, a singing synthesis model based on an attention-based sequence-to-sequence mechanism and a vocoder based on dilated causal convolutions. These two classes of mode…
Traditional Machine Learning for Pitch Detection
Thomas Drugman, Goeric Huybrechts, Viacheslav Klimkov +1
Pitch detection is a fundamental problem in speech processing as F0 is used in a large number of applications. Recent articles have proposed deep learning for robust pitch tracking…