James Qin
7 papers · 2020–2024 · 4 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 ↓
๐
Conference Polyglot ยท Bronze
๐
Interdisciplinary Bridge ยท Bronze
๐ฃ
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Keywords
automatic speech recognition
(4)
representation learning
(2)
word error rate
(2)
convolutional neural network
(2)
speech recognition
(2)
on-device speech recognition
(2)
parallel processing
(1)
connectionist temporal classification
(1)
autoregressive model
(1)
language model
(1)
masked prediction
(1)
latency reduction
(1)
on-device inference
(1)
streaming model
(1)
neural language model
(1)
end-to-end model
(1)
image token
(1)
model parameter
(1)
streaming asr
(1)
streaming speech recognition
(1)
Papers
Massive End-to-end Speech Recognition Models with Time Reduction
NAACL 2024
Self-supervised learning with random-projection quantizer for speech recognition
ICML 2022
Vector-quantized Image Modeling with Improved VQGAN
ICLR 2022
An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling
Interspeech 2021
Conformer: Convolution-augmented Transformer for Speech Recognition
Interspeech 2020
ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context
Interspeech 2020
Parallel Rescoring with Transformer for Streaming On-Device Speech Recognition
Interspeech 2020