The IBM expressive text-to-speech synthesis system for American English

@article{Pitrelli2006TheIE,
  title={The IBM expressive text-to-speech synthesis system for American English},
  author={John F. Pitrelli and Raimo Bakis and Ellen Eide and Raul Fernandez and Wael Hamza and Michael Picheny},
  journal={IEEE Transactions on Audio, Speech, and Language Processing},
  year={2006},
  volume={14},
  pages={1099-1108}
}
Expressive text-to-speech (TTS) synthesis should contribute to the pleasantness, intelligibility, and speed of speech-based human-machine interactions which use TTS. We describe a TTS engine which can be directed, via text markup, to use a variety of expressive styles, here, questioning, contrastive emphasis, and conveying good and bad news. Differences in these styles lead us to investigate two approaches for expressive TTS, a "corpus-driven" and a "prosodic-phonology" approach. Each speaker… CONTINUE READING
Highly Cited
This paper has 104 citations. REVIEW CITATIONS
63 Citations
24 References
Similar Papers

Citations

Publications citing this paper.
Showing 1-10 of 63 extracted citations

104 Citations

01020'08'11'14'17
Citations per Year
Semantic Scholar estimates that this publication has 104 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 24 references

Preservation, identification, and use of emotion in a text-tospeech system

  • E. Eide
  • Proc. IEEE Workshop on Speech Synthesis, Santa…
  • 2002
1 Excerpt

Re-defining intonation from selected units for nonuniform units based speech synthesis

  • B. Bozkurt, T. Dutoit, V. Pagel
  • Proc. SPS-IEEE Benelux Signal Process. Symp…
  • 2002
1 Excerpt

Similar Papers

Loading similar papers…