@inproceedings{40ac523e7ec8422a8bcfad86d4eda869,
title = "Fftnet: A real-time speaker-dependent neural vocoder",
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.",
keywords = "FFTNet, Neural networks, Vocoder, WaveNet",
author = "Zeyu Jin and Adam Finkelstein and Mysore, {Gautham J.} and Jingwan Lu",
note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 ; Conference date: 15-04-2018 Through 20-04-2018",
year = "2018",
month = sep,
day = "10",
doi = "10.1109/ICASSP.2018.8462431",
language = "English (US)",
isbn = "9781538646588",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2251--2255",
booktitle = "2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings",
address = "United States",
}