Arman Kaliyev
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Arman Kaliyev has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Yuri Matveev
ITMO University
4 shared publications - Elena Lyakso
St. Petersburg State University
2 shared publications - Sergey V. Rybin
ITMO University, St. Petersburg, Russia
2 shared publications - Сергей Витальевич Рыбин
Санкт-Петербургский государственный электротехнический университет «ЛЭТИ» имени В. И. Ульянова (Ленина) (СПбГЭТУ «ЛЭТИ»)
2 shared publications Aigerim K. Buribayeva
Scientific research Institute “Artificial Intelligence”, L. N. Gumilyov Eurasian National University, Astana, Kazakhstan
1 shared publication- Aleksey Grigorev
St. Petersburg State University
1 shared publication
Latest Publications
- 15 April 2021
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 24 (3) , 729-735
GAN acoustic model for Kazakh speech synthesis
- 15 April 2021
- Published by Springer Nature in International Journal of Speech Technology
- Vol. 24 (3) , 729-735
GAN acoustic model for Kazakh speech synthesis
- Open Access
- 1 October 2019
- Published by ITMO University in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
- Vol. 19 (5) , 951-954
Acoustic modeling for Kazakh speech synthesis
We present a new framework of generative adversarial network for training of acoustic model for speech synthesis. The proposed generative adversarial network consists of a generator and a pair of agent discriminators, where the generator predicts the acoustic features from the linguistic representation. Training and testing were carried out on the Kazakh speech corpus, which consisted of 5.6 hours of speech recording. According to the experiment results the 3.46 mean opinion score was obtained which shows an acceptable quality of speech synthesis. This approach of the acoustic model development can be applied in speech synthesis systems of the other languages.
- 1 October 2019
- Published by ITMO University in Scientific and Technical Journal of Information Technologies, Mechanics and Optics
- Vol. 19 (5) , 951-954
Open AccessAcoustic modeling for Kazakh speech synthesis
We present a new framework of generative adversarial network for training of acoustic model for speech synthesis. The proposed generative adversarial network consists of a generator and a pair of agent discriminators, where the generator predicts the acoustic features from the linguistic representation. Training and testing were carried out on the Kazakh speech corpus, which consisted of 5.6 hours of speech recording. According to the experiment results the 3.46 mean opinion score was obtained which shows an acceptable quality of speech synthesis. This approach of the acoustic model development can be applied in speech synthesis systems of the other languages.
- 24 July 2019
- Published by Springer Nature
- p. 299-308
AD-Child.Ru: Speech Corpus for Russian Children with Atypical Development
- 24 July 2019
- Published by Springer Nature
- p. 299-308
AD-Child.Ru: Speech Corpus for Russian Children with Atypical Development
- 24 July 2019
- Published by Springer Nature
- p. 201-208
LSTM-Based Kazakh Speech Synthesis
- Open Access
- 28 June 2019
- Published by St. Petersburg Electrotechnical University LETI in Computer tools in education
- No. 1,p. 5-28
Speech Synthesis: Past and Present
Жуpнал Компьютеpные инстpументы в обpазовании выходит с января 1998 года. Научное направление периодического издания: автоматизация и автоматизированные системы в образовании, информатика и информационные технологии. Журнал входит в перечень ведущих рецензируемых научных журналов и изданий, в которых должны быть опубликованы основные научные результаты диссертаций на соискание ученых степеней доктора и кандидата наук. Выходит в печатной и электронной версиях с дисковым приложением
- 28 June 2019
- Published by St. Petersburg Electrotechnical University LETI in Computer tools in education
- No. 1,p. 5-28
Open AccessSpeech Synthesis: Past and Present
Жуpнал Компьютеpные инстpументы в обpазовании выходит с января 1998 года. Научное направление периодического издания: автоматизация и автоматизированные системы в образовании, информатика и информационные технологии. Журнал входит в перечень ведущих рецензируемых научных журналов и изданий, в которых должны быть опубликованы основные научные результаты диссертаций на соискание ученых степеней доктора и кандидата наук. Выходит в печатной и электронной версиях с дисковым приложением
- 13 August 2017
- Published by Springer Nature
- p. 741-747
The Pausing Method Based on Brown Clustering and Word Embedding
- 13 August 2017
- Published by Springer Nature
- p. 741-747
The Pausing Method Based on Brown Clustering and Word Embedding
- 1 November 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1094-1099
Semantic neural network model of morphological rules of the agglutinative languages
The paper presents a formalization of morphological rules agglutinative languages as an example of Kazakh language. For formalization of morphological rules is proposed to use semantic neural network.
- 1 November 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1094-1099
Semantic neural network model of morphological rules of the agglutinative languages
The paper presents a formalization of morphological rules agglutinative languages as an example of Kazakh language. For formalization of morphological rules is proposed to use semantic neural network.