A methodology is proposed for emotional text-to-speech using emotional data collection, transfer-learning-based annotation of expressiveness features, and fine-tuning of a neutral TTS model.
The ryerson audio-visual database of emotional speech and song (ravdess): A dynamic, multimodal set of facial and vocal expressions in north american english,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Methodology for Controlling the Emotional Expressiveness in Synthetic Speech -- a Deep Learning approach
A methodology is proposed for emotional text-to-speech using emotional data collection, transfer-learning-based annotation of expressiveness features, and fine-tuning of a neutral TTS model.