Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
Prosodic Processing for the Automatic Synthesis of Emotional Russian Speech. / Kaliyev, Arman; Matveev, Yuri N.; Lyakso, Elena E.; Rybin, Sergey V.
Proceedings of the 2018 IEEE International Conference "Quality Management, Transport and Information Security, Information Technologies", IT and QM and IS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. стр. 653-655 8525072 (Proceedings of the 2018 International Conference ''Quality Management, Transport and Information Security, Information Technologies'', IT and QM and IS 2018).Результаты исследований: Публикации в книгах, отчётах, сборниках, трудах конференций › статья в сборнике материалов конференции › научная › Рецензирование
}
TY - GEN
T1 - Prosodic Processing for the Automatic Synthesis of Emotional Russian Speech
AU - Kaliyev, Arman
AU - Matveev, Yuri N.
AU - Lyakso, Elena E.
AU - Rybin, Sergey V.
PY - 2018/11/5
Y1 - 2018/11/5
N2 - Currently, the automatic speech synthesis technology is undergoing significant changes due to new solutions in the field of machine learning. These solutions qualitatively improve the sound of synthesized speech, bringing it closer to natural human speech. Against the backdrop of this, as well as under the influence of business, the development of artificial emotional speech for human-machine interaction systems has received a new strong turn of development. Due to this prosodic processing for the synthesis of Russian emotional speech has become an important research direction for our research group.The article presents an algorithm for predicting pause locations for three categories of emotional speech. In particular, the authors used three corpora of emotional speech, collected according to emotional categories (neutral, excited and depressed), for training classifiers. The obtained results can be used to create a high-quality automatic synthesizer of emotional speech.
AB - Currently, the automatic speech synthesis technology is undergoing significant changes due to new solutions in the field of machine learning. These solutions qualitatively improve the sound of synthesized speech, bringing it closer to natural human speech. Against the backdrop of this, as well as under the influence of business, the development of artificial emotional speech for human-machine interaction systems has received a new strong turn of development. Due to this prosodic processing for the synthesis of Russian emotional speech has become an important research direction for our research group.The article presents an algorithm for predicting pause locations for three categories of emotional speech. In particular, the authors used three corpora of emotional speech, collected according to emotional categories (neutral, excited and depressed), for training classifiers. The obtained results can be used to create a high-quality automatic synthesizer of emotional speech.
KW - emotional speech
KW - pause prediction
KW - prosody
KW - speech synthesis
KW - statistical models
UR - http://www.scopus.com/inward/record.url?scp=85058026787&partnerID=8YFLogxK
U2 - 10.1109/ITMQIS.2018.8525072
DO - 10.1109/ITMQIS.2018.8525072
M3 - Conference contribution
AN - SCOPUS:85058026787
T3 - Proceedings of the 2018 International Conference ''Quality Management, Transport and Information Security, Information Technologies'', IT and QM and IS 2018
SP - 653
EP - 655
BT - Proceedings of the 2018 IEEE International Conference "Quality Management, Transport and Information Security, Information Technologies", IT and QM and IS 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE International Conference "Quality Management, Transport and Information Security, Information Technologies", IT and QM and IS 2018
Y2 - 24 September 2018 through 28 September 2018
ER -
ID: 42717806