Detail publikace

Parameter-Efficient Transfer Learning of Pre-Trained Transformer Models for Speaker Verification Using Adapters

PENG, J. STAFYLAKIS, T. GU, R. PLCHOT, O. MOŠNER, L. BURGET, L. ČERNOCKÝ, J.

Originální název

Parameter-Efficient Transfer Learning of Pre-Trained Transformer Models for Speaker Verification Using Adapters

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

Originální abstrakt

Recently, the pre-trained Transformer models have received a rising interest in the field of speech processing thanks to their great success in various downstream tasks. However, most fine-tuning approaches update all the parameters of the pre-trained model, which becomes prohibitive as the model size grows and sometimes results in over- fitting on small datasets. In this paper, we conduct a comprehensive analysis of applying parameter-efficient transfer learning (PETL) methods to reduce the required learnable parameters for adapting to speaker verification tasks. Specifically, during the fine-tuning process, the pre-trained models are frozen, and only lightweight modules inserted in each Transformer block are trainable (a method known as adapters). Moreover, to boost the performance in a cross- language low-resource scenario, the Transformer model is further tuned on a large intermediate dataset before directly fine-tuning it on a small dataset. With updating fewer than 4% of parameters, (our proposed) PETL-based methods achieve comparable performances with full fine-tuning methods (Vox1-O: 0.55%, Vox1-E: 0.82%, Vox1-H:1.73%).

Klíčová slova

Speaker verification, pre-trained model, adapter, fine-tuning, transfer learning

Autoři

PENG, J.; STAFYLAKIS, T.; GU, R.; PLCHOT, O.; MOŠNER, L.; BURGET, L.; ČERNOCKÝ, J.

Vydáno

4. 6. 2023

Nakladatel

IEEE Signal Processing Society

Místo

Rhodes Island

ISBN

978-1-7281-6327-7

Kniha

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Strany od

1

Strany do

5

Strany počet

5

URL

https://ieeexplore.ieee.org/document/10094795

BibTex

@inproceedings{BUT185200,
  author="PENG, J. and STAFYLAKIS, T. and GU, R. and PLCHOT, O. and MOŠNER, L. and BURGET, L. and ČERNOCKÝ, J.",
  title="Parameter-Efficient Transfer Learning of Pre-Trained Transformer Models for Speaker Verification Using Adapters",
  booktitle="ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
  year="2023",
  pages="1--5",
  publisher="IEEE Signal Processing Society",
  address="Rhodes Island",
  doi="10.1109/ICASSP49357.2023.10094795",
  isbn="978-1-7281-6327-7",
  url="https://ieeexplore.ieee.org/document/10094795"
}

Dokumenty

peng_icassp2023_10094795.pdf