# MiteshPuthran/Speech-Emotion-Analyzer

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

Repository: https://github.com/MiteshPuthran/Speech-Emotion-Analyzer
Canonical: https://ross.abutalabs.com/products/speech-emotion-analyzer
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: emotion, python3, deep-learning, neural-network, data-science, deep-neural-networks, speech, voice, audio-files, natural-language-processing, natural-language-understanding, speech-recognition, emotion-recognition, speech-emotion-recognition, keras
Last push: 2023-02-07T16:19:15+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3180, "days_push": 1303, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1408, forks 435 (observed 2026-08-28T04:04:38.576734+00:00)

## What it is
A Jupyter Notebook project that builds a deep learning model (CNN, with MLP and LSTM comparisons) to detect five male/female emotions from audio speech using LibROSA feature extraction on the RAVDESS and SAVEE datasets. It serves primarily as an educational example of speech emotion recognition in Python with Keras.

## Use cases
- detect emotions from speech audio
- classify emotions in voice recordings
- learn speech emotion recognition with deep learning
- extract audio features with librosa for classification
- train a CNN on RAVDESS and SAVEE datasets
- build an emotion detector from voice

## When to choose
- you want a reference notebook for speech emotion classification
- you are learning audio feature extraction and CNNs in Python
- you need a starting point using RAVDESS or SAVEE datasets

## When to avoid
- you need a production-ready emotion detection service or API
- you need real-time emotion inference
- you need more than five emotions or robust accuracy guarantees

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, audio-processing, speech-recognition, deep-learning
- domain: machine-learning, speech-processing
- platform: python
- tags: emotion-recognition, speech-emotion-recognition, keras, librosa, jupyter-notebook, cnn, audio-classification, audio, natural-language-processing

## Member repositories
- MiteshPuthran/Speech-Emotion-Analyzer (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:38.576734+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:38:34.292648+00:00, confidence not recorded.
  - readme: https://github.com/MiteshPuthran/Speech-Emotion-Analyzer (fetched 2026-08-28T04:04:38.576734+00:00, sha 7cb552819545)
- Data as of 2026-08-30T08:39:29.467469+00:00.