Training dynamic models using early exits for automatic speech recognition on resource-constrained devices
Paper
•
2309.09546
•
Published
•
1
Falavigna Daniele
falavi
AI & ML interests
automatic speech recognition
Recent Activity
authored
a paper
9 days ago
Training dynamic models using early exits for automatic speech
recognition on resource-constrained devices
authored
a paper
9 days ago
Continual Contrastive Spoken Language Understanding
authored
a paper
9 days ago
Sequence-Level Knowledge Distillation for Class-Incremental End-to-End
Spoken Language Understanding
Organizations
authored
10
papers
9 days ago
Continual Contrastive Spoken Language Understanding
Paper
•
2310.02699
•
Published
Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding
Paper
•
2305.13899
•
Published
Mixtures of Deep Neural Experts for Automated Speech Scoring
Paper
•
2106.12475
•
Published
•
2
Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters
Paper
•
2402.00828
•
Published
An Investigation of the Combination of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding
Paper
•
2211.08161
•
Published
Large Language Models Are Strong Audio-Visual Speech Recognition Learners
Paper
•
2409.12319
•
Published
Scaling strategies for on-device low-complexity source separation with Conv-Tasnet
Paper
•
2303.03005
•
Published
Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach
Paper
•
2505.14336
•
Published
•
3
Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices
Paper
•
2506.18035
•
Published
updated
a
model
2 months ago
updated
2
models
3 months ago
published
2
models
3 months ago
updated
3
models
3 months ago