58 citations · 94 across the 38 of their papers we have counts for
17 papers · 1 filter
Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages
Seraphina Fong, Marco Matassoni, Alessio Brutti
Large language models (LLMs) have demonstrated potential in handling spoken inputs for high-resource languages, reaching state-of-the-art performance in various tasks. However, the…
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,…
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…
An Experimental Review of Speaker Diarization methods with application to Two-Speaker Conversational Telephone Speech recordings
Luca Serafini, Samuele Cornell, Giovanni Morrone +3
We performed an experimental review of current diarization systems for the conversational telephone speech (CTS) domain. In detail, we considered a total of eight different algorit…
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…
End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations
Giovanni Morrone, Samuele Cornell, Luca Serafini +3
Recent works show that speech separation guided diarization (SSGD) is an increasingly promising direction, mainly thanks to the recent progress in speech separation. It performs di…
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…
Low-complexity acoustic scene classification in DCASE 2022 Challenge
Irene Martín-Morató, Francesco Paissan, Alberto Ancilotto +5
This paper presents an analysis of the Low-Complexity Acoustic Scene Classification task in DCASE 2022 Challenge. The task was a continuation from the previous years, but the low-c…
Conversational Speech Separation: an Evaluation Study for Streaming Applications
Giovanni Morrone, Samuele Cornell, Enrico Zovato +2
Continuous speech separation (CSS) is a recently proposed framework which aims at separating each speaker from an input mixture signal in a streaming fashion. Hereafter we perform…
Low-Latency Speech Separation Guided Diarization for Telephone Conversations
Giovanni Morrone, Samuele Cornell, Desh Raj +4
In this paper, we carry out an analysis on the use of speech separation guided diarization (SSGD) in telephone conversations. SSGD performs diarization by separating the speakers s…
Learning to Rank Microphones for Distant Speech Recognition
Samuele Cornell, Alessio Brutti, Marco Matassoni +1
Fully exploiting ad-hoc microphone networks for distant speech recognition is still an open issue. Empirical evidence shows that being able to select the best microphone leads to s…
Compact recurrent neural networks for acoustic event detection on low-energy low-complexity platforms
Gianmarco Cerutti, Rahul Prasad, Alessio Brutti +1
Outdoor acoustic events detection is an exciting research field but challenged by the need for complex algorithms and deep learning techniques, typically requiring many computation…
Supervised online diarization with sample mean loss for multi-domain data
Enrico Fini, Alessio Brutti
Recently, a fully supervised speaker diarization approach was proposed (UIS-RNN) which models speakers using multiple instances of a parameter-sharing recurrent neural network. In…
The Speed Submission to DIHARD II: Contributions & Lessons Learned
Md Sahidullah, Jose Patino, Samuele Cornell +11
This paper describes the speaker diarization systems developed for the Second DIHARD Speech Diarization Challenge (DIHARD II) by the Speed team. Besides describing the system, whic…