Dmitriy Serdyuk
6 papers
· 2015–2024
· 3 conferences
· across top CS/AI conferences
Achievements
π£
Hot Topic Early Bird
π§
Keyword Pioneer
π
Conference Polyglot
(3)
π
Academic Marathon
(9)
π
Cross-Pollinator
(4)
π
Renaissance Researcher
(5)
π
Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(10)
π
Conference Pioneer
Conferences
INTERSPEECH (3)
ICLR (2)
NIPS (1)
Top co-authors
Keywords
recurrent neural network
(2)
attention mechanism
(1)
speech recognition
(1)
multimodal learning
(1)
automatic speech recognition
(1)
video transformer
(1)
phoneme recognition
(1)
acoustic model
(1)
latency reduction
(1)
visual feature
(1)
audio-visual speech recognition
(1)
universal speech model
(1)
recurrent neural network transducer
(1)
online speech recognition
(1)
weight binarization
(1)
model size reduction
(1)
video feature extraction
(1)
location-aware attention
(1)
sequence generation
(1)
mouth motion
(1)
Papers
USM RNN-T model weights binarization
INTERSPEECH 2024
Deep Complex Networks
ICLR 2018
Twin Regularization for Online Speech Recognition
INTERSPEECH 2018