Daniele Falavigna

Principal Researcher, Fondazione Bruno Kessler

Joined

July 2019

Names

Daniele Falavigna (Preferred)

Emails

****@fbk.eu (Confirmed)

Personal Links

Career & Education History

Principal Researcher

Fondazione Bruno Kessler (fbk.eu)

2000 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

automatic speech recognition

Present

machine learning applied to spoken language

Present

Publications

Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach
Umberto Cappellazzo, Minsu Kim, Stavros Petridis, Daniele Falavigna, Alessio Brutti
- Interspeech
- Readers: Everyone
LDASR: An experimental study on layer drop using conformer-based architecture
Abdul Hannan, Alessio Brutti, Daniele Falavigna
- OpenReview Archive Direct Upload
- Readers: Everyone
Large Language Models are Strong Audio-Visual Speech Recognition Learners
Umberto Cappellazzo, Minsu Kim, Honglie Chen, Pingchuan Ma, Stavros Petridis, Daniele Falavigna, Alessio Brutti, Maja Pantic
- ICASSP 2025
- Readers: Everyone
Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters
Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti
- Interspeech 2024
- Readers: Everyone
PARAMETER-EFFICIENT TRANSFER LEARNING OF AUDIO SPECTROGRAM TRANSFORMERS
Umberto Cappellazzo, Daniele Falavigna, Alessio Brutti, Mirco Ravanelli
- MLSP 2025
- Readers: Everyone
Continual Contrastive Spoken Language Understanding
Umberto Cappellazzo, Enrico Fini, Muqiao Yang, Daniele Falavigna, Alessio Brutti, Bhiksha Raj
- Submitted to ICLR 2024
- Readers: Everyone
TranscRater: a Tool for Automatic Speech Recognition Quality Estimation
Shahab Jalalvand, Matteo Negri, Marco Turchi, José G. C. de Souza, Daniele Falavigna, Mohammed R. H. Qwaider
- 2016 (modified: 13 Nov 2022)
- ACL (System Demonstrations) 2016
- Readers: Everyone
Driving ROVER with Segment-based ASR Quality Estimation
Shahab Jalalvand, Matteo Negri, Daniele Falavigna, Marco Turchi
- 2015 (modified: 16 Jul 2019)
- ACL (1) 2015
- Readers: Everyone
Multitask Learning for Adaptive Quality Estimation of Automatically Transcribed Utterances
José G. C. de Souza, Hamed Zamani, Matteo Negri, Marco Turchi, Daniele Falavigna
- 2015 (modified: 16 Jul 2019)
- HLT-NAACL 2015
- Readers: Everyone
Person Identification Using Multiple Cues.
Roberto Brunelli, Daniele Falavigna
- 1995 (modified: 10 Nov 2022)
- IEEE Trans. Pattern Anal. Mach. Intell.1995
- Readers: Everyone

Co-Authors