2 papers
eess.AS2021
An objective evaluation of the effects of recording conditions and speaker characteristics in multi-speaker deep neural speech synthesis
Beata Lorincz, Adriana Stan, Mircea Giurgiu
Multi-speaker spoken datasets enable the creation of text-to-speech synthesis (TTS) systems which can output several voice identities. The multi-speaker (MSPK) scenario also enable…
eess.AS2021
Speaker verification-derived loss and data augmentation for DNN-based multispeaker speech synthesis
Beata Lorincz, Adriana Stan, Mircea Giurgiu
Building multispeaker neural network-based text-to-speech synthesis systems commonly relies on the availability of large amounts of high quality recordings from each speaker and co…