OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Mevonai Speech Emotion Recognition

Mevonai Speech Emotion Recognition is an open-source Python machine-learning project that diarizes multi-speaker audio and predicts emotion labels from MFCC features using a convolutional neural network.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Mevonai Speech Emotion Recognition — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want to inspect a repository-based workflow for multi-speaker emotion analysis, try its linked Colab notebook, or process WAV files locally.

Who it is for

  • Developers exploring speech emotion recognition or speaker diarization.
  • Researchers and learners working with audio features and convolutional models.
  • Call-centre teams evaluating an audio-analysis approach for customer-satisfaction feedback.

Documented uses

  • Separate a call recording into speaker turns.
  • Generate emotion predictions for analyzed audio.
  • Explore or train an emotion-recognition model using the project notebooks.
Before you choose

Requirements & limits

The project is available as a public GitHub repository under the MIT license. Its README links to a Google Colab demo and documents Docker and Python virtual-environment setup paths.

  • The local workflow expects WAV files in src/input/.
  • The README describes speaker diarization, MFCC feature extraction and a TensorFlow-Keras CNN.
  • The README says a pretrained model is included and provides a separate notebook for training with the RAVDESS emotional-speech dataset.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run emotion analysis on local WAV files

Use the documented local workflow to process WAV audio and locate diarized files and emotion predictions.

Before you start

  • A local Python environment with Python 3 and the project dependencies installed through the repository's setup script.
  • WAV audio files to place in the project's src/input/ directory.

Steps

  1. Create and activate a Python virtual environment.

  2. Clone the repository, change into its src directory, and run setup.sh.

  3. Place WAV audio files in src/input/ and run python3 speechEmotionRecognition.py.

  4. Find diarized files in src/output/ and emotion predictions in a CSV file under src/.

Expected outcome

The project processes the input audio using its included pretrained model and produces diarized files and emotion predictions.

Guide limitations

  • The README describes WAV input for this workflow.
  • The repository documents a local workflow; it does not establish a hosted service interface.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
8 October 2026
Original website title
SuyashMore/MevonAI-Speech-Emotion-Recognition · Official homepage title · retained in its source language
How we review sourcesSuggest a correction