Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition

September 17, 2022 Β· Declared Dead Β· πŸ› Interspeech

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Ye Bai, Jie Li, Wenjing Han, Hao Ni, Kaituo Xu, Zhuo Zhang, Cheng Yi, Xiaorui Wang arXiv ID 2209.08326 Category eess.AS: Audio & Speech Cross-listed cs.CL Citations 4 Venue Interspeech Last Checked 3 months ago
Abstract
While transformers and their variant conformers show promising performance in speech recognition, the parameterized property leads to much memory cost during training and inference. Some works use cross-layer weight-sharing to reduce the parameters of the model. However, the inevitable loss of capacity harms the model performance. To address this issue, this paper proposes a parameter-efficient conformer via sharing sparsely-gated experts. Specifically, we use sparsely-gated mixture-of-experts (MoE) to extend the capacity of a conformer block without increasing computation. Then, the parameters of the grouped conformer blocks are shared so that the number of parameters is reduced. Next, to ensure the shared blocks with the flexibility of adapting representations at different levels, we design the MoE routers and normalization individually. Moreover, we use knowledge distillation to further improve the performance. Experimental results show that the proposed model achieves competitive performance with 1/3 of the parameters of the encoder, compared with the full-parameter model.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Audio & Speech

Died the same way β€” πŸ‘» Ghosted