shitian-ni/speech-recognition-transfer-learning

Speech command recognition DenseNet transfer learning from UrbanSound8k in keras tensorflow

29
/ 100
Experimental

This project helps you quickly build a system to recognize specific spoken commands, like "yes," "no," or "stop." It takes existing audio recordings of everyday sounds and adapts that knowledge to understand new short voice commands. Anyone working on voice-controlled devices, accessibility tools, or interactive voice response systems would find this useful.

No commits in the last 6 months.

Use this if you need to train a speech command recognition system using a relatively small dataset of voice commands, leveraging a pre-existing, larger dataset of general urban sounds.

Not ideal if you're building a system for transcribing full sentences or need to recognize speech in a language not represented in the available transfer learning datasets.

voice-control speech-recognition audio-processing embedded-systems human-computer-interaction
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

17

Forks

5

Language

Python

License

Last pushed

Jan 19, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/shitian-ni/speech-recognition-transfer-learning"

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