Результаты исследований: Иные виды публикаций › иная › научная
Reducing over-smoothness in speech synthesis using Generative Adversarial Networks. / Pavlovskiy, Evgeniy N.; Шэн, Лэюань .
2018.Результаты исследований: Иные виды публикаций › иная › научная
}
TY - GEN
T1 - Reducing over-smoothness in speech synthesis using Generative Adversarial Networks
AU - Pavlovskiy, Evgeniy N.
AU - Шэн, Лэюань
PY - 2018
Y1 - 2018
N2 - Speech synthesis is widely used in many practical applications. In recent years, speech synthesis technology has developed rapidly. However, one of the reasons why synthetic speech is unnatural is that it often has over-smoothness. In order to improve the naturalness of synthetic speech, we first extract the mel-spectrogram of speech and convert it into a real image, then take the over-smooth mel-spectrogram image as input, and use image-to-image translation Generative Adversarial Networks(GANs) framework to generate a more realistic mel-spectrogram. Finally, the results show that this method greatly reduces the over-smoothness of synthesized speech and is more close to the mel-spectrogram of real speech
AB - Speech synthesis is widely used in many practical applications. In recent years, speech synthesis technology has developed rapidly. However, one of the reasons why synthetic speech is unnatural is that it often has over-smoothness. In order to improve the naturalness of synthetic speech, we first extract the mel-spectrogram of speech and convert it into a real image, then take the over-smooth mel-spectrogram image as input, and use image-to-image translation Generative Adversarial Networks(GANs) framework to generate a more realistic mel-spectrogram. Finally, the results show that this method greatly reduces the over-smoothness of synthesized speech and is more close to the mel-spectrogram of real speech
M3 - Other contribution
ER -
ID: 18919853