A speech-deepfake dataset for ten public figures built with transcription-based segmentation reports high synthetic naturalness (NISQA 3.69) and a human misclassification rate of 61.9%.
Deep Learning Based Assessment of Synthetic Speech Naturalness
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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.
fields
eess.AS 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Collecting, Curating, and Annotating Good Quality Speech deepfake dataset for Famous Figures: Process and Challenges
A speech-deepfake dataset for ten public figures built with transcription-based segmentation reports high synthetic naturalness (NISQA 3.69) and a human misclassification rate of 61.9%.