Deep Learning Based Assessment of Synthetic Speech Naturalness
arXiv:2104.11673 · doi:10.21437/Interspeech.2020-2382
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.
arXiv commentLate upload, presented at Interspeech 2020
References in corpus (2)
Cited by in corpus (10)
- NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets
- 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
- Evaluating gesture generation in a large-scale open challenge: The GENEA Challenge 2022
- Bias-Aware Loss for Training Image and Speech Quality Prediction Models from Multiple Datasets
- Learning and controlling the source-filter representation of speech with a variational autoencoder
- SVSNet: An End-to-end Speaker Voice Similarity Assessment Model
- Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features
- Wideband Audio Waveform Evaluation Networks: Efficient, Accurate Estimation of Speech Qualities
- Predicting pairwise preferences between TTS audio stimuli using parallel ratings data and anti-symmetric twin neural networks