Experiments with signal-driven symbolic prosody for statistical parametric speech synthesis

By Fabio Tesser, Giacomo Sommavilla, Giulio Paci, Piero Cosi. 2013

8 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xu Tan
2. Eric Battenberg
3. Hung-yi Lee
4. Wei-Ning Hsu
5. Ron J. Weiss
6. R. Skerry-Ryan
7. Daisy Stanton
8. Da-Rong Liu

Citations in the corpus

• Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron (2018, methodology): “(Tesser et al., 2013) proposes the use of “signal driven” features to predict symbolic prosody representations, using AuToBI labels to improve HMM-based synthesis.”
• Improving Unsupervised Style Transfer in end-to-end Speech Synthesis with end-to-end Speech Recognition (2018, background): “Recently, some work try to improve multi-speaker TTS with speaker verification [12, 13].”
• Improving Prosody Modelling with Cross-Utterance Bert Embeddings for End-to-End Speech Synthesis (2020, unknown): “Symbolic prosody labels [9] are widely used as features for both HMMbased and deep-learning-based SPSS systems[6, 10, 11].”