Deep Learning Based Assessment of Synthetic Speech Naturalness

Abstract

In this paper, we present a new objective prediction model for synthetic speech naturalness. It can be used to evaluate Text-To-Speech or Voice Conversion systems and works language independently. The model is trained end-to-end and based on a CNN-LSTM network that previously showed to give good results for speech quality estimation. We trained and tested the model on 16 different datasets, such as from the Blizzard Challenge and the Voice Conversion Challenge. Further, we show that the reliability of deep learning-based naturalness prediction can be improved by transfer learning from speech quality prediction models that are trained on objective POLQA scores. The proposed model is made publicly available and can, for example, be used to evaluate different TTS system configurations.

Late upload, presented at Interspeech 2020

References in corpus (1)

• AutoMOS: Learning a non-intrusive assessor of naturalness-of-speech

Cited by in corpus (3)

• The GENEA Challenge 2022: A large evaluation of data-driven co-speech gesture generation
• A large, crowdsourced evaluation of gesture generation systems on common data: The GENEA Challenge 2020
• Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks