Olivier Siohan
9 papers · 2017–2023 · 2 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (17) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze
👥
Mega-Team · Squad
📈
Trend Setter
Venues
Top co-authors
Research topics
Speech & Audio
(8)
Recognition
(8)
Deep Learning
(6)
Machine Learning
(4)
Architectures
(3)
Learning Types · Deep Learning
(3)
Application Areas
(2)
Techniques
(2)
Artificial Intelligence
(1)
Computer Vision
(1)
Analysis
(1)
Core AI
(1)
Core Methods
(1)
Learning Types · Machine Learning
(1)
Optimization & Theory
(1)
Keywords
connectionist temporal classification
(3)
recurrent neural network transducer
(3)
automatic speech recognition
(3)
speech recognition
(2)
overlapping speech
(2)
audio-visual speech recognition
(2)
acoustic modeling
(1)
foundation model
(1)
visual context
(1)
phone recognition
(1)
acoustic unit
(1)
model ensemble
(1)
visual feature
(1)
end-to-end model
(1)
neural network model
(1)
multi-channel speech recognition
(1)
sequence training
(1)
end-to-end speech recognition
(1)
video transformer
(1)
multimodal learning
(1)
Papers
Cascaded encoders for fine-tuning ASR models on overlapped speech
Interspeech 2023
Revisiting the Entropy Semiring for Neural Speech Recognition
ICLR 2023
End-to-End multi-talker audio-visual ASR using an active speaker attention module
Interspeech 2022
Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Muti-Person Video
Interspeech 2022
Bridging the Gap Between Streaming and Non-Streaming ASR Systems by Distilling Ensembles of CTC and RNN-T Models
Interspeech 2021
End-to-End Audio-Visual Speech Recognition for Overlapping Speech
Interspeech 2021
Acoustic Modeling for Google Home
Interspeech 2017
Annealed f-Smoothing as a Mechanism to Speed up Neural Network Training
Interspeech 2017
CTC Training of Multi-Phone Acoustic Models for Speech Recognition
Interspeech 2017