Edward Lin
6 papers · 2013–2022 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Bronze π Academic Marathon Β· Sprint π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (14) π£ Hot Topic Early Bird
π
Trend Setter
Venues
Top co-authors
Research topics
Machine Learning
(5)
Speech & Audio
(4)
Learning Types Β· Machine Learning
(4)
Deep Learning
(3)
Recognition
(3)
Natural Language Processing
(2)
Architectures
(2)
Core Methods
(2)
Generation
(2)
Synthesis
(2)
Artificial Intelligence
(1)
Core AI
(1)
Learning Types Β· Deep Learning
(1)
Understanding
(1)
Keywords
automatic speech recognition
(2)
word error rate
(2)
error correction
(2)
non-autoregressive generation
(2)
low-resource language
(1)
long short-term memory
(1)
edit distance
(1)
beam search
(1)
sequence-to-sequence model
(1)
non-autoregressive translation
(1)
speech recognition error
(1)
byte pair encoding
(1)
masking strategy
(1)
punctuation prediction
(1)
multilingual punctuation prediction
(1)
speech recognition readability
(1)
speech translation segmentation
(1)
neural network
(1)
text error correction
(1)
encoder decoder
(1)
Papers
Mask the Correct Tokens: An Embarrassingly Simple Approach for Error Correction
EMNLP 2022
FastCorrect 2: Fast Error Correction on Multiple Candidates for Automatic Speech Recognition
EMNLP 2021
FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition
NeurIPS 2021
A 43 Language Multilingual Punctuation Prediction Neural Network Model
Interspeech 2020
An End-to-End Architecture of Online Multi-Channel Speech Separation
Interspeech 2020
This Text Has the Scent of Starbucks: A Laplacian Structured Sparsity Model for Computational Branding Analytics
EMNLP 2013