SuyashMore/MevonAI-Speech-Emotion-Recognition
Identify the emotion of multiple speakers in an Audio Segment
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.
Stars
179
Forks
46
Language
C
License
MIT
Category
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.
Higher-rated alternatives
salute-developers/GigaAM
Foundational Model for Speech Recognition Tasks
AkishinoShiame/Chinese-Speech-Emotion-Datasets
Datasets of A Deep Convolutional Neural Network Based Virtual Elderly Companion Agent.
habla-liaa/ser-with-w2v2
Official implementation of INTERSPEECH 2021 paper 'Emotion Recognition from Speech Using Wav2vec...
NotAbhinavGamerz/emotion-aware-automatic-speech-recognition
🎤 Enhance speech recognition by detecting emotions in spoken language, combining OpenAI's...
jsugg/ser
The AI-powered ser Python package is a tool for recognizing and analyzing emotions in speech....