Geodesic
Creating a database for modeling system for speech
News of the Kabardin-Balkar scientific center of RAS, no. 6-2 (2018), pp. 181-186.

Voir la notice de l'article provenant de la source Math-Net.Ru

The stages of creating a phonetic-acoustic database, adapted for learning the system of automatic speech synthesis based on deep convolutional neural networks, are described. A phonetic transcriptor designed with consideration of the grapheme-phonemic transformations of the Chechen language is presented.
Keywords: speech database, automatic synthesis of Chechen speech, end-to-end speech synthesis system, machine learning, phonetic transcriptor. 
@article{IZKAB_2018_6-2_a16,
     author = {E. S. Izrailova},
     title = {Creating a database for modeling system for speech},
     journal = {News of the Kabardin-Balkar scientific center of RAS},
     pages = {181--186},
     publisher = {mathdoc},
     number = {6-2},
     year = {2018},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/IZKAB_2018_6-2_a16/}
}
TY  - JOUR
AU  - E. S. Izrailova
TI  - Creating a database for modeling system for speech
JO  - News of the Kabardin-Balkar scientific center of RAS
PY  - 2018
SP  - 181
EP  - 186
IS  - 6-2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/IZKAB_2018_6-2_a16/
LA  - ru
ID  - IZKAB_2018_6-2_a16
ER  - 
%0 Journal Article
%A E. S. Izrailova
%T Creating a database for modeling system for speech
%J News of the Kabardin-Balkar scientific center of RAS
%D 2018
%P 181-186
%N 6-2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/IZKAB_2018_6-2_a16/
%G ru
%F IZKAB_2018_6-2_a16
E. S. Izrailova. Creating a database for modeling system for speech. News of the Kabardin-Balkar scientific center of RAS, no. 6-2 (2018), pp. 181-186. http://geodesic.mathdoc.fr/item/IZKAB_2018_6-2_a16/

[1] E. S. Izrailova, “O sozdanii fonetiko-akusticheskoi bazy v ramkakh sinteza chechenskoi rechi”, Vestnik Voronezhskogo gosudarstvennogo universiteta. Seriya: Sistemnyi analiz i informatsionnye tekhnologii, 2017, no. 2, 111–115

[2] Aaron van den Oord, Sander Dieleman, Heiga Zen, WaveNet: A Generative Model for Raw Audio, (data obrascheniya: 12.09.2018, elektronnyi resurs) https://deepmind.com/blog/wavenet-generative-model-raw-audio/

[3] J. Sotelo et al, “Char2wav: End-to-end speech synthesis”, Proc. ICLR, 2017 | Zbl

[4] S. Arik et al, “Deep voice: Real-time neural text-to-speech”, Proc. ICML, 2017, 195–204

[5] K. Cho et al, “Learning phrase representations using RNN encoder-decoder for statistical machine translation”, Proc. EMNLP, 2014, 1724–1734 pp.

[6] Hideyuki Tachibana, Katsuya Uenoyama, Shunsuke Aihara, Efficiently trainable text-to-speech system based on deep convolutional networks with guided attention, arXiv: (data obrascheniya 19.11.2018, elektronnyi resurs) 1710.08969

[7] [Elektronnyi resurs], (data obrascheniya 19.11.2018) https://www.radiomarsho.com/z/17557

[8] E. S. Izrailova, “Foneticheskii alfavit chechenskogo yazyka kak osnova sistemy sinteza rechi”, NTI. ser. 2. Inform. protsessy i sistemy, 2018, no. 2, 35–39, VINITI RAN