MiteshPuthran/Speech-Emotion-Analyzer

The neural network model is capable of detecting five different male/female emotions from audio speeches. (Deep Learning, NLP, Python)

51
/ 100
Established

Extracts audio features using LibROSA (MFCC, spectral analysis) normalized to 3-second windows with doubled sampling rates to augment limited training data. Uses a CNN architecture that outperformed LSTM and MLP baselines, achieving >70% emotion classification accuracy while maintaining 100% gender detection precision across RAVDESS and SAVEE datasets. Supports real-time inference on custom audio input for downstream applications like autonomous vehicle safety systems or emotion-adaptive marketing.

1,403 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,403

Forks

437

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 07, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MiteshPuthran/Speech-Emotion-Analyzer"

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