George Sterpu

16 papers A 1B 3Journal 9Unranked 3

Year	Rank	Type	Title / Venue / Authors
2023	—	`conf`	Data Center Audio/Video Intelligence on Device (DAVID) - An Edge-AI Platform for Smart-Toys. SpeD Gabriel Cosache, Francisco Salgado, Rishabh Jain, Cosmin Rotariu, George Sterpu, Peter Corcoran
2023	J	`jnl`	Data Center Audio/Video Intelligence on Device (DAVID) - An Edge-AI Platform for Smart-Toys. CoRR Gabriel Cosache, Francisco Salgado, Cosmin Rotariu, George Sterpu, Rishabh Jain, Peter Corcoran
2022	J	`jnl`	Taris: An online speech recognition framework with sequence to sequence neural networks for both audio-only and audio-visual speech. Comput. Speech Lang. George Sterpu, Naomi Harte
2021	—	`conf`	Learning to Count Words in Fluent Speech Enables Online Speech Recognition. SLT George Sterpu, Christian Saam, Naomi Harte
2020	J	`jnl`	AV Taris: Online Audio-Visual Speech Recognition. CoRR George Sterpu, Naomi Harte
2020	J	`jnl`	How to Teach DNNs to Pay Attention to the Visual Modality in Speech Recognition. CoRR George Sterpu, Christian Saam, Naomi Harte
2020	J	`jnl`	How to Teach DNNs to Pay Attention to the Visual Modality in Speech Recognition. IEEE ACM Trans. Audio Speech Lang. Process. George Sterpu, Christian Saam, Naomi Harte
2020	J	`jnl`	Learning to Count Words in Fluent Speech enables Online Speech Recognition. CoRR George Sterpu, Christian Saam, Naomi Harte
2020	A	`conf`	Should we Hard-Code the Recurrence Concept or Learn it Instead ? Exploring the Transformer Architecture for Audio-Visual Speech Recognition. INTERSPEECH George Sterpu, Christian Saam, Naomi Harte
2020	J	`jnl`	Should we hard-code the recurrence concept or learn it instead ? Exploring the Transformer architecture for Audio-Visual Speech Recognition. CoRR George Sterpu, Christian Saam, Naomi Harte
2018	B	`conf`	Attention-based Audio-Visual Fusion for Robust Automatic Speech Recognition. ICMI George Sterpu, Christian Saam, Naomi Harte
2018	J	`jnl`	Attention-based Audio-Visual Fusion for Robust Automatic Speech Recognition. CoRR George Sterpu, Christian Saam, Naomi Harte
2018	B	`conf`	Can DNNs Learn to Lipread Full Sentences? ICIP George Sterpu, Christian Saam, Naomi Harte
2018	J	`jnl`	Can DNNs Learn to Lipread Full Sentences? CoRR George Sterpu, Christian Saam, Naomi Harte
2018	B	`conf`	Large Vocabulary Continuous Audio-Visual Speech Recognition. ICMI George Sterpu
2017	—	`conf`	Towards Lipreading Sentences with Active Appearance Models. AVSP George Sterpu, Naomi Harte