Joint Federated Learning and Personalization for on-Device ASR
In this paper, we propose a joint federated learning (FL) and personalization method for on-
device ASR adaptation. Starting with a Conformer-based RNN-T as the ASR model …
device ASR adaptation. Starting with a Conformer-based RNN-T as the ASR model …
OODIn: An optimised on-device inference framework for heterogeneous mobile devices
SI Venieris, I Panopoulos… - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
Radical progress in the field of deep learning (DL) has led to unprecedented accuracy in
diverse inference tasks. As such, deploying DL models across mobile platforms is vital to …
diverse inference tasks. As such, deploying DL models across mobile platforms is vital to …
Speech Understanding on Tiny Devices with A Learning Cache
This paper addresses spoken language understanding (SLU) on microcontroller-like
embedded devices, integrating on-device execution with cloud offloading in a novel fashion …
embedded devices, integrating on-device execution with cloud offloading in a novel fashion …
How to reach real-time AI on consumer devices? Solutions for programmable and custom architectures
The unprecedented performance of deep neural networks (DNNs) has led to large strides in
various Artificial Intelligence (AI) inference tasks, such as object and speech recognition …
various Artificial Intelligence (AI) inference tasks, such as object and speech recognition …
CoMFLP: Correlation Measure based Fast Search on ASR Layer Pruning
Transformer-based speech recognition (ASR) model with deep layers exhibited significant
performance improvement. However, the model is inefficient for deployment on resource …
performance improvement. However, the model is inefficient for deployment on resource …
Leveraging cache to enable SLU on tiny devices
This paper addresses spoken language understanding (SLU) on microcontroller-like
embedded devices, integrating on-device execution with cloud offloading in a novel fashion …
embedded devices, integrating on-device execution with cloud offloading in a novel fashion …
Towards an Open-Source Dutch Speech Recognition System for the Healthcare Domain
C Tejedor-García, B van der Molen… - Proceedings of the …, 2022 - aclanthology.org
The current largest open-source generic automatic speech recognition (ASR) system for
Dutch, Kaldi_NL, does not include a domain-specific healthcare jargon in the lexicon …
Dutch, Kaldi_NL, does not include a domain-specific healthcare jargon in the lexicon …
Size and Inference Time Optimized Automatic Speech Recognition Model
In this work, development of an efficient optimized Automatic Speech Recognition (ASR)
system is done by leveraging methodologies. This study focuses on knowledge distillation, a …
system is done by leveraging methodologies. This study focuses on knowledge distillation, a …
[PDF][PDF] Challenges on the Promising Road to Automatic Speech Recognition of Privacy-Sensitive Dutch Doctor-Patient Consultation Recordings
B van der Molen, C Tejedor García, H Heuvel… - 2022 - repository.ubn.ru.nl
In this paper we present the currently running PDI-SSH project Homo Medicinalis (HoMed),
in which we use machine learning to build an Automatic Speech Recognition (ASR) …
in which we use machine learning to build an Automatic Speech Recognition (ASR) …