1ytic/edit-distance-papers
A curated list of papers dedicated to edit-distance as objective function
This list compiles research papers focused on directly optimizing 'edit distance' as a performance measure for sequence prediction tasks. It helps researchers understand how to train models that improve sequence-level accuracy, like Word Error Rate (WER) in speech recognition, rather than just word-level correctness. The resource is for machine learning researchers and practitioners working on tasks where the final output is a sequence of elements.
No commits in the last 6 months.
Use this if you are a researcher or engineer encountering 'exposure bias' or 'loss evaluation mismatch' when training sequence-to-sequence models with proxy loss functions.
Not ideal if you are looking for an introductory explanation of edit distance or general machine learning optimization techniques, as this list focuses on specific advanced research problems.
Stars
53
Forks
2
Language
—
License
—
Category
Last pushed
Aug 22, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/1ytic/edit-distance-papers"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TensorSpeech/TensorFlowASR
:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2....
dangvansam/viet-asr
VietASR - Vietnamese Automatic Speech Recognition
wenet-e2e/wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit
xinjli/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
srvk/eesen
The official repository of the Eesen project