Copertina

Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ali, Mohamed Nabih, Brutti, Alessio, Falavigna, Daniele
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MLMA: Towards Multilingual ASR With Mamba-based Architectures
di: Ali, Mohamed Nabih, et al.
Pubblicazione: (2025)

Input Conditioned Layer Dropping in Speech Foundation Models
di: Hannan, Abdul, et al.
Pubblicazione: (2025)

Training dynamic models using early exits for automatic speech recognition on resource-constrained devices
di: Wright, George August, et al.
Pubblicazione: (2023)

Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices
di: Lasbordes, Maxence, et al.
Pubblicazione: (2025)

The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence
di: Gaido, Marco, et al.
Pubblicazione: (2025)

FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian
di: Papi, Sara, et al.
Pubblicazione: (2025)

MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
di: Gaido, Marco, et al.
Pubblicazione: (2024)

Federated Heterogeneous Language Model Optimization for Hybrid Automatic Speech Recognition
di: Hong, Mengze, et al.
Pubblicazione: (2026)

Distillation-based Layer Dropping (DLD): Effective End-to-end Framework for Dynamic Speech Networks
di: Hannan, Abdul, et al.
Pubblicazione: (2026)

Large Language Models are Strong Audio-Visual Speech Recognition Learners
di: Cappellazzo, Umberto, et al.
Pubblicazione: (2024)

Recurrent Early Exits for Federated Learning with Heterogeneous Clients
di: Lee, Royson, et al.
Pubblicazione: (2024)

Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters
di: Cappellazzo, Umberto, et al.
Pubblicazione: (2024)

An Effective Training Framework for Light-Weight Automatic Speech Recognition Models
di: Hannan, Abdul, et al.
Pubblicazione: (2025)

Dynamic Early Exit in Reasoning Models
di: Yang, Chenxu, et al.
Pubblicazione: (2025)

Speech LLMs in Low-Resource Scenarios: Data Volume Requirements and the Impact of Pretraining on High-Resource Languages
di: Fong, Seraphina, et al.
Pubblicazione: (2025)

Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach
di: Cappellazzo, Umberto, et al.
Pubblicazione: (2025)

Categorize Early, Integrate Late: Divergent Processing Strategies in Automatic Speech Recognition
di: Roll, Nathan, et al.
Pubblicazione: (2026)

Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers
di: Cappellazzo, Umberto, et al.
Pubblicazione: (2023)

Dynamic Data Pruning for Automatic Speech Recognition
di: Xiao, Qiao, et al.
Pubblicazione: (2024)

Contextualized Automatic Speech Recognition with Dynamic Vocabulary
di: Sudo, Yui, et al.
Pubblicazione: (2024)

Early Exit Is a Natural Capability in Transformer-based Models: An Empirical Study on Early Exit without Joint Optimization
di: Shan, Weiqiao, et al.
Pubblicazione: (2024)

Automatic Speech Recognition for the Ika Language
di: Nzenwata, Uchenna, et al.
Pubblicazione: (2024)

ADEPT: Adaptive Dynamic Early-Exit Process for Transformers
di: Yoo, Sangmin, et al.
Pubblicazione: (2026)

End-to-end Automatic Speech Recognition and Speech Translation: Integration of Speech Foundational Models and LLMs
di: Luu, Nam, et al.
Pubblicazione: (2025)

Qualitative Evaluation of Language Model Rescoring in Automatic Speech Recognition
di: Bañeras-Roux, Thibault, et al.
Pubblicazione: (2026)

Dynamic Vocabulary Pruning in Early-Exit LLMs
di: Vincenti, Jort, et al.
Pubblicazione: (2024)

Synthetic Voice Data for Automatic Speech Recognition in African Languages
di: DeRenzi, Brian, et al.
Pubblicazione: (2025)

BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts
di: Bajpai, Divya Jyoti, et al.
Pubblicazione: (2025)

Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges
di: Liu, Dancheng, et al.
Pubblicazione: (2024)

Responsible Benchmarking of Fairness for Automatic Speech Recognition
di: Herron, Felix, et al.
Pubblicazione: (2026)

Vietnamese Automatic Speech Recognition: A Revisit
di: Vu, Thi, et al.
Pubblicazione: (2026)

Augmenting Automatic Speech Recognition Models with Disfluency Detection
di: Amann, Robin, et al.
Pubblicazione: (2024)

WhisperPipe: A Resource-Efficient Streaming Architecture for Real-Time Automatic Speech Recognition
di: Ramezani, Erfan, et al.
Pubblicazione: (2026)

Uni-ASR: Unified LLM-Based Architecture for Non-Streaming and Streaming Automatic Speech Recognition
di: Xia, Yinfeng, et al.
Pubblicazione: (2026)

NEAT: Neuron-Based Early Exit for Large Reasoning Models
di: Liu, Kang, et al.
Pubblicazione: (2026)

Evaluation of Automatic Speech Recognition Using Generative Large Language Models
di: Bañeras-Roux, Thibault, et al.
Pubblicazione: (2026)

CIF-T: A Novel CIF-based Transducer Architecture for Automatic Speech Recognition
di: Zhang, Tian-Hao, et al.
Pubblicazione: (2023)

Automatic Speech Recognition for Hindi
di: Saha, Anish, et al.
Pubblicazione: (2024)

Contextualized Automatic Speech Recognition with Dynamic Vocabulary Prediction and Activation
di: Lin, Zhennan, et al.
Pubblicazione: (2025)

OWSM-Biasing: Contextualizing Open Whisper-Style Speech Models for Automatic Speech Recognition with Dynamic Vocabulary
di: Sudo, Yui, et al.
Pubblicazione: (2025)