Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification

Xiaoyang Qu, Jianzong Wang, Jing Xiao


State-of-the-art speaker verification models are based on deep learning techniques, which heavily depend on the hand-designed neural architectures from experts or engineers. We borrow the idea of neural architecture search (NAS) for the text-independent speaker verification task. As NAS can learn deep network structures automatically, we introduce the NAS conception into the well-known x-vector network. Furthermore, this paper proposes an evolutionary algorithm enhanced neural architecture search method called Auto-Vector to automatically discover promising networks for the speaker verification task. The experimental results demonstrate our NAS-based model outperforms state-of-the-art speaker verification models.


 DOI: 10.21437/Interspeech.2020-3057

Cite as: Qu, X., Wang, J., Xiao, J. (2020) Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification. Proc. Interspeech 2020, 961-965, DOI: 10.21437/Interspeech.2020-3057.


@inproceedings{Qu2020,
  author={Xiaoyang Qu and Jianzong Wang and Jing Xiao},
  title={{Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification}},
  year=2020,
  booktitle={Proc. Interspeech 2020},
  pages={961--965},
  doi={10.21437/Interspeech.2020-3057},
  url={http://dx.doi.org/10.21437/Interspeech.2020-3057}
}