amanbasu/speech-emotion-recognition

Detecting emotions using MFCC features of human speech using Deep Learning

47
/ 100
Emerging

This project helps you analyze human speech to detect underlying emotions. You provide raw audio recordings, and it classifies the speaker's emotion as happy, sad, angry, frustrated, neutral, or fear. This tool is useful for anyone working with spoken interactions, such as customer service managers, qualitative researchers, or content creators.

133 stars. No commits in the last 6 months.

Use this if you need to automatically identify the emotional tone of speech in audio files.

Not ideal if you require very high accuracy for critical decision-making, as the reported accuracy is 45%.

speech-analysis customer-service-analytics qualitative-research content-moderation sentiment-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

133

Forks

38

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

Dec 02, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/amanbasu/speech-emotion-recognition"

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