Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
Emotional Speech Recognition of Holocaust Survivors with Deep Neural Network Models for Russian Language. / Bukreeva, Liudmila; Guseva, Daria; Dolgushin, Mikhail; Evdokimova, Vera; Obotnina, Vasilisa.
Speech and Computer. 2023. p. 68-76 6 (Lecture Notes in Computer Science; Vol. 14338).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
}
TY - GEN
T1 - Emotional Speech Recognition of Holocaust Survivors with Deep Neural Network Models for Russian Language
AU - Bukreeva, Liudmila
AU - Guseva, Daria
AU - Dolgushin, Mikhail
AU - Evdokimova, Vera
AU - Obotnina, Vasilisa
PY - 2023/11/22
Y1 - 2023/11/22
N2 - Recognition of highly emotional speech remains a challenging case of automatic speech recognition task. The aim of this article is to carry out experiments on highly emotional speech recognition by investigating oral history archives provided by the Yad Vashem foundation. The material consists of elderly peoples’ emotional speech full of accents and common language. We analyze and preprocess 26 h of publicly available video interviews with Holocaust survivors. Our objective was to develop a system able to perform emotional speech recognition based on deep neural network models. We present and evaluate the obtained results that contribute to the research field of oral history archives.
AB - Recognition of highly emotional speech remains a challenging case of automatic speech recognition task. The aim of this article is to carry out experiments on highly emotional speech recognition by investigating oral history archives provided by the Yad Vashem foundation. The material consists of elderly peoples’ emotional speech full of accents and common language. We analyze and preprocess 26 h of publicly available video interviews with Holocaust survivors. Our objective was to develop a system able to perform emotional speech recognition based on deep neural network models. We present and evaluate the obtained results that contribute to the research field of oral history archives.
KW - Corpora
KW - Question Answering
KW - Visual History Archives
UR - https://www.mendeley.com/catalogue/5522248e-a4e0-3c7a-88e3-36cef66102a6/
U2 - 10.1007/978-3-031-48309-7_6
DO - 10.1007/978-3-031-48309-7_6
M3 - Conference contribution
SN - 9783031483080
T3 - Lecture Notes in Computer Science
SP - 68
EP - 76
BT - Speech and Computer
Y2 - 29 November 2023 through 1 December 2023
ER -
ID: 114283490