Picture for Daniele Falavigna

Daniele Falavigna

Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients

Add code
May 27, 2024
Viaarxiv icon

Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters

Add code
Feb 01, 2024
Viaarxiv icon

Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers

Add code
Dec 07, 2023
Viaarxiv icon

Continual Contrastive Spoken Language Understanding

Add code
Oct 04, 2023
Viaarxiv icon

Training dynamic models using early exits for automatic speech recognition on resource-constrained devices

Add code
Sep 18, 2023
Viaarxiv icon

Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding

Add code
May 23, 2023
Viaarxiv icon

Improving the Intent Classification accuracy in Noisy Environment

Add code
Mar 12, 2023
Viaarxiv icon

Scaling strategies for on-device low-complexity source separation with Conv-Tasnet

Add code
Mar 06, 2023
Viaarxiv icon

Exploring the Joint Use of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding

Add code
Nov 15, 2022
Viaarxiv icon

Seed Words Based Data Selection for Language Model Adaptation

Add code
Jul 20, 2021
Figure 1 for Seed Words Based Data Selection for Language Model Adaptation
Figure 2 for Seed Words Based Data Selection for Language Model Adaptation
Figure 3 for Seed Words Based Data Selection for Language Model Adaptation
Figure 4 for Seed Words Based Data Selection for Language Model Adaptation
Viaarxiv icon