no code implementations • 10 May 2024 • Jie Xu, Karthikeyan Saravanan, Rogier Van Dalen, Haaris Mehmood, David Tuckey, Mete Ozay
We therefore propose an adaptation method that can be combined with differential privacy and call it DP-DyLoRA.
no code implementations • 22 Jan 2024 • Jisi Zhang, Vandana Rajan, Haaris Mehmood, David Tuckey, Pablo Peso Parada, Md Asif Jalal, Karthikeyan Saravanan, Gil Ho Lee, Jungin Lee, Seokyeong Jung
On-device Automatic Speech Recognition (ASR) models trained on speech data of a large population might underperform for individuals unseen during training.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 6 Jun 2022 • Haaris Mehmood, Agnieszka Dobrowolska, Karthikeyan Saravanan, Mete Ozay
To this end, we propose FedNST, a novel method for training distributed ASR models using private and unlabelled user data.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3