Name: Umberto Cappellazzo
Type: User
Company: University of Trento/Fondazione Bruno Kessler
Bio: PhD candidate @ University of Trento. Interests: Continual Learning and efficient finetuning for speech.Now working on Multimodal LLMs @ Imperial College London
Twitter: Umberto_Senpai
Location: Trento
Umberto Cappellazzo's Projects
Auto-AVSR: Lip-Reading Sentences Project + LLMs
An anthology of recent continual learning papers, where people interested in this fascinating topic can start discovering its multidimensional representations.
"An Investigation of the Combination of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding", accepted at INTERSPEECH 2023.
A clean and simple data loading library for Continual Learning
Forked icefall for early-exit integration and combination with Flowers for federated-learning ASR. [JSALT2023]
This is the official repository of the papers "Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers" and "Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters".
"Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding", accepted at INTERSPEECH 2023.
A demo for defining a CIL scenario for SLURP and how to train a seq2seq model on that.
A collection of papers related to speech language models
A framework for automatic speech recognition