Alert button
Picture for Daniele Falavigna

Daniele Falavigna

Alert button

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

Feb 01, 2024
Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti

Viaarxiv icon

Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers

Dec 07, 2023
Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti, Mirco Ravanelli

Viaarxiv icon

Continual Contrastive Spoken Language Understanding

Oct 04, 2023
Umberto Cappellazzo, Enrico Fini, Muqiao Yang, Daniele Falavigna, Alessio Brutti, Bhiksha Raj

Figure 1 for Continual Contrastive Spoken Language Understanding
Figure 2 for Continual Contrastive Spoken Language Understanding
Figure 3 for Continual Contrastive Spoken Language Understanding
Figure 4 for Continual Contrastive Spoken Language Understanding
Viaarxiv icon

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

Sep 18, 2023
George August Wright, Umberto Cappellazzo, Salah Zaiem, Desh Raj, Lucas Ondel Yang, Daniele Falavigna, Alessio Brutti

Figure 1 for Training dynamic models using early exits for automatic speech recognition on resource-constrained devices
Figure 2 for Training dynamic models using early exits for automatic speech recognition on resource-constrained devices
Figure 3 for Training dynamic models using early exits for automatic speech recognition on resource-constrained devices
Figure 4 for Training dynamic models using early exits for automatic speech recognition on resource-constrained devices
Viaarxiv icon

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

May 23, 2023
Umberto Cappellazzo, Muqiao Yang, Daniele Falavigna, Alessio Brutti

Figure 1 for Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding
Figure 2 for Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding
Figure 3 for Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding
Figure 4 for Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding
Viaarxiv icon

Improving the Intent Classification accuracy in Noisy Environment

Mar 12, 2023
Mohamed Nabih Ali, Alessio Brutti, Daniele Falavigna

Figure 1 for Improving the Intent Classification accuracy in Noisy Environment
Figure 2 for Improving the Intent Classification accuracy in Noisy Environment
Figure 3 for Improving the Intent Classification accuracy in Noisy Environment
Figure 4 for Improving the Intent Classification accuracy in Noisy Environment
Viaarxiv icon

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

Mar 06, 2023
Mohamed Nabih Ali, Francesco Paissan, Daniele Falavigna, Alessio Brutti

Figure 1 for Scaling strategies for on-device low-complexity source separation with Conv-Tasnet
Figure 2 for Scaling strategies for on-device low-complexity source separation with Conv-Tasnet
Figure 3 for Scaling strategies for on-device low-complexity source separation with Conv-Tasnet
Figure 4 for Scaling strategies for on-device low-complexity source separation with Conv-Tasnet
Viaarxiv icon

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

Nov 15, 2022
Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti

Figure 1 for Exploring the Joint Use of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding
Figure 2 for Exploring the Joint Use of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding
Figure 3 for Exploring the Joint Use of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding
Figure 4 for Exploring the Joint Use of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding
Viaarxiv icon

Seed Words Based Data Selection for Language Model Adaptation

Jul 20, 2021
Roberto Gretter, Marco Matassoni, Daniele Falavigna

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

Mixtures of Deep Neural Experts for Automated Speech Scoring

Jun 23, 2021
Sara Papi, Edmondo Trentin, Roberto Gretter, Marco Matassoni, Daniele Falavigna

Figure 1 for Mixtures of Deep Neural Experts for Automated Speech Scoring
Figure 2 for Mixtures of Deep Neural Experts for Automated Speech Scoring
Figure 3 for Mixtures of Deep Neural Experts for Automated Speech Scoring
Viaarxiv icon