Skip to content

EmoPP

Predict pauses to add emotion to speech synthesis

Visit official site

What EmoPP is

The model is described as an emotion-aware prosody analysis approach that finds emotional cues in speech and predicts better pause positions. It serves end-to-end speech synthesis.

What you can do with it

  • Analyze prosody linked to emotion
  • Predict where pauses should fall
  • Support expressive synthetic voices

What to watch out for

  • The stated setting is end-to-end synthesis
  • Observation is tied to the ESD dataset
  • Listed uses include voice assistants

Pros & cons

✓ What we like

  • Dialogue systems and voice assistants are listed
  • Emotional cues are drawn from speech

! What to watch out for

  • The model targets end-to-end synthesis
  • The ESD dataset is used for observation

FAQ

What does it predict?

More suitable pause positions in speech.

Which dataset is named?

The ESD dataset is named for observation.

Last reviewed: 2026-11-15

More AI audio tools tools

View all →

How we review