2 citations · 6 across the 16 of their papers we have counts for
16 papers
SpeechLLM Meets Federated Learning for End-to-End ASR: English and Italian Case Studies
Mohamed Nabih Ali, Daniele Falavigna, Alessio Brutti
Federated learning (FL) enables privacy-preserving training of automatic speech recognition (ASR) systems across distributed data sources, yet its application to large-scale speech…
Distillation-based Layer Dropping (DLD): Effective End-to-end Framework for Dynamic Speech Networks
Abdul Hannan, Daniele Falavigna, Shah Nawaz +3
Edge devices operate in constrained and varying resource settings, requiring dynamic architectures that can adapt to limitations of the available resources. To meet such demands, l…
MLMA: Towards Multilingual ASR With Mamba-based Architectures
Mohamed Nabih Ali, Daniele Falavigna, Alessio Brutti
Multilingual automatic speech recognition (ASR) remains a challenging task, especially when balancing performance across high- and low-resource languages. Recent advances in sequen…
Input Conditioned Layer Dropping in Speech Foundation Models
Abdul Hannan, Daniele Falavigna, Alessio Brutti
Curating foundation speech models for edge and IoT settings, where computational resources vary over time, requires dynamic architectures featuring adaptable reduction strategies.…
Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices
Maxence Lasbordes, Daniele Falavigna, Alessio Brutti
The ability to dynamically adjust the computational load of neural models during inference in a resource aware manner is crucial for on-device processing scenarios, characterised b…
Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach
Umberto Cappellazzo, Minsu Kim, Stavros Petridis +2
Audio-Visual Speech Recognition (AVSR) enhances robustness in noisy environments by integrating visual cues. While recent advances integrate Large Language Models (LLMs) into AVSR,…
Large Language Models are Strong Audio-Visual Speech Recognition Learners
Umberto Cappellazzo, Minsu Kim, Honglie Chen +5
Multimodal large language models (MLLMs) have recently become a focal point of research due to their formidable multimodal understanding capabilities. For example, in the audio and…
Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients
Mohamed Nabih Ali, Alessio Brutti, Daniele Falavigna
Automatic speech recognition models require large amounts of speech recordings for training. However, the collection of such data often is cumbersome and leads to privacy concerns.…
Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters
Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti
Mixture of Experts (MoE) architectures have recently started burgeoning due to their ability to scale model's capacity while maintaining the computational cost affordable. Furtherm…
Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers
Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti +1
Parameter-efficient transfer learning (PETL) methods have emerged as a solid alternative to the standard full fine-tuning approach. They only train a few extra parameters for each…
Continual Contrastive Spoken Language Understanding
Umberto Cappellazzo, Enrico Fini, Muqiao Yang +3
Recently, neural networks have shown impressive progress across diverse fields, with speech processing being no exception. However, recent breakthroughs in this area require extens…
Training dynamic models using early exits for automatic speech recognition on resource-constrained devices
George August Wright, Umberto Cappellazzo, Salah Zaiem +5
The ability to dynamically adjust the computational load of neural models during inference is crucial for on-device processing scenarios characterised by limited and time-varying c…
Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding
Umberto Cappellazzo, Muqiao Yang, Daniele Falavigna +1
The ability to learn new concepts sequentially is a major weakness for modern neural networks, which hinders their use in non-stationary environments. Their propensity to fit the c…
Improving the Intent Classification accuracy in Noisy Environment
Mohamed Nabih Ali, Alessio Brutti, Daniele Falavigna
Intent classification is a fundamental task in the spoken language understanding field that has recently gained the attention of the scientific community, mainly because of the fea…
Scaling strategies for on-device low-complexity source separation with Conv-Tasnet
Mohamed Nabih Ali, Francesco Paissan, Daniele Falavigna +1
Recently, several very effective neural approaches for single-channel speech separation have been presented in the literature. However, due to the size and complexity of these mode…
An Investigation of the Combination of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding
Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti
Continual learning refers to a dynamical framework in which a model receives a stream of non-stationary data over time and must adapt to new data while preserving previously acquir…