R1ckShi/AESRC2020

[ICASSP2021] Data preperation scripts, training pipeline and baseline experiment results for the Interspeech 2020 Accented English Speech Recognition Challenge (AESRC).

43
/ 100
Emerging

This project helps researchers and practitioners in speech technology prepare data and train models for accented English speech recognition and accent identification. It takes raw audio data and corresponding transcripts as input, processes them, and outputs trained speech recognition models capable of handling various English accents. Speech researchers, machine learning engineers working on voice AI, or linguists focused on accent analysis would use this.

No commits in the last 6 months.

Use this if you need to build or benchmark models for recognizing speech in different English accents or identifying the accent itself, leveraging established challenge datasets and frameworks.

Not ideal if you are looking for a plug-and-play solution for general speech recognition without specific interest in accent challenges or developing custom models.

speech-recognition accent-identification voice-ai linguistics machine-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

56

Forks

18

Language

Python

License

Apache-2.0

Last pushed

Oct 09, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/R1ckShi/AESRC2020"

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