ICASSP 2018accepted0 citations

Fftnet: A Real-Time Speaker-Dependent Neural Vocoder

Zeyu Jin, Adam Finkelstein, Gautham J. Mysore, Jingwan Lu

Abstract

We introduce FFTNet, a deep learning approach synthesizing audio waveforms. Our approach builds on the recent WaveNet project, which showed that it was possible to synthesize a natural sounding audio waveform directly from a deep convolutional neural network. FFTNet offers two improvements over WaveNet. First it is substantially faster, allowing for real-time synthesis of audio waveforms. Second, when used as a vocoder, the resulting speech sounds more natural, as measured via a “mean opinion score” test.

BibTeX
@inproceedings{icassp2018_fftnetarealtimes,
  title = {Fftnet: A Real-Time Speaker-Dependent Neural Vocoder},
  author = {Zeyu Jin and Adam Finkelstein and Gautham J. Mysore and Jingwan Lu},
  booktitle = {ICASSP 2018},
  year = {2018}
}