Generative Models for Improved Naturalness, Intelligibility, and Voicing of Whispered Speech

This work adapts two recent architectures of generative models and evaluates their effectiveness for the conversion of whispered speech to normal speech. We incorporate the normal target speech into the training criterion of vector-quantized variational autoencoders (VQ-VAEs) and Mel-GANs, thereby c...

Celý popis

Podrobná bibliografia

Vydané v:	2022 IEEE Spoken Language Technology Workshop (SLT) s. 943 - 948
Hlavní autori:	Wagner, Dominik, Bayerl, Sebastian P., Maruri, Hector A. Cordourier, Bocklet, Tobias
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	IEEE 09.01.2023
Predmet:	Adaptation models Cepstral analysis Conferences Distortion Distortion measurement GAN generative models speech conversion Task analysis Training VAE whispered speech
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!