• DOI:10.21437/interspeech.2020-2861
Corpus ID: 221703703

Controllable neural text-to-speech synthesis using intuitive prosodic features

@inproceedings{Raitio2020ControllableNT,
  title={Controllable neural text-to-speech synthesis using intuitive prosodic features},
  author={T. Raitio and Ramya Rasipuram and Dan Castellani},
  booktitle={INTERSPEECH},
  year={2020}
}

T. Raitio, Ramya Rasipuram, Dan Castellani

Published in INTERSPEECH 2020

Computer Science, Engineering

Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the prosody of generated utterances often represents the average prosodic style of the database instead of having wide prosodic variation. Moreover, the generated prosody is solely defined by the input text, which does not allow for different styles for the same sentence. In this work, we train a sequence-to-sequence neural network conditioned on acoustic speech features to… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed