# Renovamen/Speech-Emotion-Recognition

Speech emotion recognition implemented in Keras (LSTM, CNN, SVM, MLP) | 语音情感识别

Repository: https://github.com/Renovamen/Speech-Emotion-Recognition
Canonical: https://ross.abutalabs.com/products/speech-emotion-recognition
Language: Python
License: MIT
License Family: permissive
Topics: speech-emotion-recognition, lstm, svm, mlp, opensmile, cnn
Last push: 2023-03-25T01:20:48+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": 2703, "days_push": 1258, "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 1314, forks 230 (observed 2026-08-28T04:04:20.411517+00:00)

## What it is
A Python library implementing speech emotion recognition with Keras/TensorFlow 2 using LSTM, CNN, SVM, and MLP models. It extracts audio features via librosa or OpenSMILE and achieves roughly 80% accuracy on standard emotion datasets.

## Use cases
- classify emotions in audio recordings
- train a speech emotion recognition model
- extract features from speech audio with librosa or opensmile
- recognize emotion from wav files
- benchmark emotion recognition on RAVDESS or EMO-DB
- learn how to build audio classification models in Keras

## When to choose
- you need a ready-made speech emotion recognition pipeline in Python
- you want to compare LSTM, CNN, SVM, and MLP on emotion classification
- you are working with RAVDESS, SAVEE, EMO-DB, or CASIA datasets

## When to avoid
- you need real-time or production-scale emotion recognition
- you need pretrained models for languages or datasets not covered here
- you need a maintained actively developed project

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, audio-processing, speech-recognition, deep-learning
- domain: machine-learning, speech-processing
- platform: python, cross-platform
- tags: speech-emotion-recognition, keras, lstm, cnn, svm, mlp, librosa, opensmile, audio-classification, audio, natural-language-processing

## Member repositories
- Renovamen/Speech-Emotion-Recognition (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:20.411517+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 2026-08-30T04:48:45.229947+00:00, confidence not recorded.
  - readme: https://github.com/Renovamen/Speech-Emotion-Recognition (fetched 2026-08-28T04:04:20.411517+00:00, sha 2f535256fcec)
- Data as of 2026-08-30T08:39:29.467469+00:00.