Chanwoo Kim
Ph.D. Brown University 2011 (ORCID 0000-0003-0193-8167)
Facts
6 properties- Instance of
- human
- Occupation
- researcher
- Employer
- University of Wisconsin–Madison (2014–present), University of Cambridge (2011–2014)[2]
- Educated at
- Brown University (2006–2011), Seoul National University (2001–2006), Brown University[3]
- Doctoral student
- Yunbai Cao[5]
🏷️ Also known as
en Chanwoo Kim
🔖 Identifiers · 4
- ORCID iD
- 0000-0003-0193-8167
- MR Author ID
- 959580
- Mathematics Genealogy Project ID
- 155038
- ResearchGate profile ID
- Chanwoo_Kim11
🔗 Connections
Author of 9
Attention Based On-Device Streaming Speech Recognition with Large Speech Corpus,
End-to-End Training of a Large Vocabulary End-to-End Speech Recognition System,
Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home,
Hierarchical Multi-Stage Word-to-Grapheme Named Entity Corrector for Automatic Speech Recognition,
Improved Multi-Stage Training of Online Attention-Based Encoder-Decoder Models,
Improved Vocal Tract Length Perturbation for a State-of-the-Art End-to-End Speech Recognition System,
Multi-Task Multi-Resolution Char-to-BPE Cross-Attention Decoder for End-to-End Speech Recognition,
Power-Law Nonlinearity with Maximally Uniform Distribution Criterion for Improved Neural Network Training in Automatic Speech Recognition
+1 more
← Authored by 9
Attention Based On-Device Streaming Speech Recognition with Large Speech Corpus,
End-to-End Training of a Large Vocabulary End-to-End Speech Recognition System,
Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home,
Hierarchical Multi-Stage Word-to-Grapheme Named Entity Corrector for Automatic Speech Recognition,
Improved Multi-Stage Training of Online Attention-Based Encoder-Decoder Models,
Improved Vocal Tract Length Perturbation for a State-of-the-Art End-to-End Speech Recognition System,
Multi-Task Multi-Resolution Char-to-BPE Cross-Attention Decoder for End-to-End Speech Recognition,
Power-Law Nonlinearity with Maximally Uniform Distribution Criterion for Improved Neural Network Training in Automatic Speech Recognition
+1 more
Affiliated with 2
Press Enter · cited answer in seconds