HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition

13 April 2022

Papers citing "HuBERT-EE: Early Exiting HuBERT for Efficient Speech Recognition"

10 / 10 papers shown

Title
DAISY: Data Adaptive Self-Supervised Early Exit for Speech Representation Models T. Lin Hung-yi Lee Hao Tang 40 1 0 08 Jun 2024
OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification Yifan Peng Yui Sudo Muhammad Shakeel Shinji Watanabe VLM 37 17 0 20 Feb 2024
Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference Kai Li Yi Luo 26 2 0 06 Dec 2023
Big model only for hard audios: Sample dependent Whisper model selection for efficient inferences Hugo Malard Salah Zaiem Robin Algayres 31 2 0 22 Sep 2023
Training dynamic models using early exits for automatic speech recognition on resource-constrained devices George August Wright Umberto Cappellazzo Salah Zaiem Desh Raj Lucas Ondel Yang Daniele Falavigna Mohamed Nabih Ali A. Brutti 22 2 0 18 Sep 2023
Fine-tuning Strategies for Faster Inference using Speech Self-Supervised Models: A Comparative Study Salah Zaiem Robin Algayres Titouan Parcollet S. Essid Mirco Ravanelli 52 14 0 12 Mar 2023
Understanding the Robustness of Multi-Exit Models under Common Corruptions Akshay Mehra Skyler Seto Navdeep Jaitly B. Theobald AAML 16 3 0 03 Dec 2022
Avoid Overthinking in Self-Supervised Models for Speech Recognition Dan Berrebbi Brian Yan Shinji Watanabe LRM 20 4 0 01 Nov 2022
Intermediate Loss Regularization for CTC-based Speech Recognition Jaesong Lee Shinji Watanabe 118 135 0 05 Feb 2021
Don't shoot butterfly with rifles: Multi-channel Continuous Speech Separation with Early Exit Transformer Sanyuan Chen Yu-Huan Wu Zhuo Chen Takuya Yoshioka Shujie Liu Jinyu Li 29 26 0 23 Oct 2020