SuyashMore/MevonAI-Speech-Emotion-Recognition

Identify the emotion of multiple speakers in an Audio Segment

48
/ 100
Emerging

Combines speaker diarization (partitioning audio by speaker identity) with MFCC feature extraction and a CNN classifier to isolate and emotionally classify each speaker's segments independently. The pipeline uses librosa for audio processing, TensorFlow-Keras for a 2D convolutional architecture trained on RAVDESS datasets, and outputs emotion predictions per speaker to CSV. Includes Docker deployment and processes .wav files locally, making it suitable for call center feedback analysis workflows.

179 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

179

Forks

46

Language

C

License

MIT

Last pushed

Feb 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/SuyashMore/MevonAI-Speech-Emotion-Recognition"

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