stevenhillis/awesome-asr-contextualization

A curated list of awesome papers on contextualizing E2E ASR outputs

37
/ 100
Emerging

Getting accurate transcriptions of spoken words can be tricky, especially for unusual terms like proper nouns, jargon, or rare words. This list compiles academic papers that explore techniques to improve the accuracy of Automatic Speech Recognition (ASR) systems for these specific words by leveraging context. Speech scientists and engineers would use this resource to find research on how to make ASR outputs more reliable for critical terms.

No commits in the last 6 months.

Use this if you are developing or researching ASR systems and need to improve their accuracy when transcribing specialized vocabulary, names, or industry-specific terms.

Not ideal if you are an end-user simply looking for an off-the-shelf speech-to-text application for general use, rather than researching ASR system enhancements.

speech-recognition natural-language-processing audio-transcription AI-research linguistics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

80

Forks

8

Language

License

Apache-2.0

Last pushed

May 10, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/stevenhillis/awesome-asr-contextualization"

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