34 citations · 116 across the 19 of their papers we have counts for
4 papers · 1 filter
NHSS: A Speech and Singing Parallel Database
Bidisha Sharma, Xiaoxue Gao, Karthika Vijayan +2
We present a database of parallel recordings of speech and singing, collected and released by the Human Language Technology (HLT) laboratory at the National University of Singapore…
Optimizing voice conversion network with cycle consistency loss of speaker identity
Hongqiang Du, Xiaohai Tian, Lei Xie +1
We propose a novel training scheme to optimize voice conversion network with a speaker identity loss function. The training scheme not only minimizes frame-level spectral loss, but…
High quality voice conversion using prosodic and high-resolution spectral features
Hy Quy Nguyen, Siu Wa Lee, Xiaohai Tian +2
Voice conversion methods have advanced rapidly over the last decade. Studies have shown that speaker characteristics are captured by spectral feature as well as various prosodic fe…
A Waveform Representation Framework for High-quality Statistical Parametric Speech Synthesis
Bo Fan, Siu Wa Lee, Xiaohai Tian +2
State-of-the-art statistical parametric speech synthesis (SPSS) generally uses a vocoder to represent speech signals and parameterize them into features for subsequent modeling. Ma…