saiteja-talluri/Speech2Face

Implementation of the CVPR 2019 Paper - Speech2Face: Learning the Face Behind a Voice by MIT CSAIL

47
/ 100
Emerging

This tool helps researchers and forensic analysts explore the relationship between voice and facial features. By inputting an audio clip of a person speaking, it generates a set of facial characteristics that are likely to belong to the speaker. This is designed for those studying speech recognition, biometric identification, or human perception.

178 stars. No commits in the last 6 months.

Use this if you are a researcher or a student in a relevant field and want to investigate how a person's voice can predict aspects of their face.

Not ideal if you need to reconstruct a photorealistic image of a person's face from their voice, as it currently outputs facial features, not a complete image.

speech-recognition-research biometric-identification forensic-analysis computational-linguistics human-computer-interaction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

178

Forks

37

Language

Python

License

MIT

Last pushed

Mar 24, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/saiteja-talluri/Speech2Face"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.