Fetching the paper…

Reading the bibliography…

TalkNet: Fully-Convolutional Non-Autoregressive Speech Synthesis Model · Around

2020

TalkNet: Fully-Convolutional Non-Autoregressive Speech Synthesis Model

Beliaev, Stanislav, Rebryk, Yurii, Ginsburg, Boris

Original
PDF
Post on X

Understand

We propose TalkNet, a convolutional non-autoregressive neural model for speech synthesis.

The model consists of two feed-forward convolutional networks.
The first network predicts grapheme durations.
An input text is expanded by repeating each symbol according to the predicted duration.

Built on

P. Taylor,
2009
Earlier work this paper cites.
P. J. A. Cock
2009
Earlier work this paper cites.
D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,”
Original
2014
Earlier work this paper cites.
H. Zen and H. Sak, “Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis,” in
2015
Earlier work this paper cites.
H. Zen, Y. Agiomyrgiannakis, N. Egberts, F. Henderson, and P. Szczepaniak, “Fast, compact, and high quality LSTM-RNN based statistical parametric speech synthesizers for mobile devices,” in
2016
Earlier work this paper cites.

Similar

Y. Taigman, L. Wolf, A. Polyak, and E. Nachmani, “VoiceLoop: Voice fitting and synthesis via a phonological loop,”
Original
2017
Cited alongside, same era.
S. Ö. Arik
Original
2017
Cited alongside, same era.
A. Gibiansky
2017
Cited alongside, same era.
A. Vaswani
2017
Cited alongside, same era.
P. Micikevicius
Original
2017
Cited alongside, same era.

Then

R. Prenger, R. Valle, and B. Catanzaro, “WaveGlow: A flow-based generative network for speech synthesis,” in
2019
Later among the works it cites.
K. Peng, W. Ping, Z. Song, and K. Zhao, “Parallel neural text-to-speech,”
Original
2019
Later among the works it cites.
O. Kuchaiev
Original
2019
Later among the works it cites.
S. Kriman
2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…