Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
George Sterpu
Observed name:
Sterpu, George
Institution:
Xperi (Ireland)
Observed institutions:
Trinity College Dublin,
Xperi (Ireland),
Xperi (United States),
Universitatea Națională de Știință și Tehnologie Politehnica București
ORCID:
0000-0002-8724-9188
Observed ORCID:
0000-0002-8724-9188
OpenAlex ID:
A5034046565
Attention-based Audio-Visual Fusion for Robust Automatic Speech Recognition
2018
·
George Sterpu
, Christian Saam
, et al.
·
INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION
·
77
PDF
How to Teach DNNs to Pay Attention to the Visual Modality in Speech Recognition
2020
·
George Sterpu
, Christian Saam
, et al.
·
IEEE/ACM Transactions on Audio Speech and Language Processing
·
37
PDF
Towards Lipreading Sentences with Active Appearance Models
2017
·
George Sterpu
, Naomi Harte
·
International Conference on Auditory-Visual Speech Processing (AVSP)
·
21
PDF
Should we Hard-Code the Recurrence Concept or Learn it Instead ? Exploring the Transformer Architecture for Audio-Visual Speech Recognition
2020
·
George Sterpu
, Christian Saam
, et al.
·
Interspeech (USB)
·
11
PDF
Can DNNs Learn to Lipread Full Sentences?
2018
·
George Sterpu
, Christian Saam
, et al.
·
Proceedings - International Conference on Image Processing
·
11
Taris: An online speech recognition framework with sequence to sequence neural networks for both audio-only and audio-visual speech
2022
·
George Sterpu
, Naomi Harte
·
Computer Speech & Language
·
7
PDF
Learning to Count Words in Fluent Speech Enables Online Speech Recognition
2021
·
George Sterpu
, Christian Saam
, et al.
·
IEEE Spoken Language Technology Workshop (SLT)
·
6
PDF
Can DNNs Learn to Lipread Full Sentences?
2018
·
Sterpu, George
, Saam, Christian
, et al.
·
arXiv (Cornell University)
·
2
PDF
Data Center Audio/Video Intelligence on Device (DAVID) - An Edge-AI Platform for Smart-Toys
2023
·
Gabriel Cosache
, Francisco Salgado
, et al.
·
International Conference on Speech Technology and Human-Computer Dialogue (SpeD)
·
1
PDF
Deep Cross-Modal Alignment in Audio-Visual Speech Recognition
2021
·
George Sterpu
·
Trinity's Access to Research Output (TARA) (Trinity College Dublin)
·
1
PDF
AV Taris: Online Audio-Visual Speech Recognition
2020
·
Sterpu, George
, Harte, Naomi
·
arXiv (Cornell University)
·
1
PDF
Large Vocabulary Continuous Audio-Visual Speech Recognition
2018
·
George Sterpu
·
INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION
VIBSYS: Integrated didactic and research platform for Vibration Analysis
2013
·
Grigore Stamatescu
, George Sterpu
, et al.
Show more works
View as search
Works count:
14
Citation count:
179
H-index:
6
I10-index:
5
Year
Topic
Type
