Evolutionary Algorithm Enhanced Neural Architecture Search for Text-Independent Speaker Verification
This work addresses the need for automated architecture design in speaker verification, offering a domain-specific improvement over manual expert methods.
The paper tackled the problem of designing neural architectures for text-independent speaker verification by introducing an evolutionary algorithm-enhanced neural architecture search (Auto-Vector) to automatically discover networks, resulting in a model that outperforms state-of-the-art speaker verification models.
State-of-the-art speaker verification models are based on deep learning techniques, which heavily depend on the handdesigned neural architectures from experts or engineers. We borrow the idea of neural architecture search(NAS) for the textindependent 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.