alefiury/SE-R-2022-SER-Track

Code for the winning solution in the SE&R 2022 Challenge - SER track.

31
/ 100
Emerging

This project offers a solution for automatically identifying emotions in spoken Portuguese audio. It takes raw audio segments as input and classifies them into 'neutral,' 'non-neutral female,' or 'non-neutral male' emotional states. This would primarily be used by researchers and practitioners working on speech analysis, emotion recognition, or natural language processing for Portuguese.

No commits in the last 6 months.

Use this if you need to analyze Portuguese speech recordings to detect emotional content, especially for spontaneous and prepared speech.

Not ideal if your primary goal is general-purpose Automatic Speech Recognition (transcription) rather than emotion analysis, or if you are working with languages other than Portuguese.

Speech Emotion Recognition Portuguese Language Processing Acoustic Analysis Computational Linguistics Audio Sentiment Analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

16

Forks

2

Language

Python

License

Apache-2.0

Last pushed

Mar 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/alefiury/SE-R-2022-SER-Track"

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