Evolutionary Algorithm Enhanced Neural Architecture Search For Text-independent Speaker Verification

Abstract

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.

Stats

• citations11
• S2 citations—
• github stars0
• HF likes0
• heat score8.09
• arxiv keyqu2020evolutionary

Related papers

• Speechnas: Towards Better Trade-off Between Latency And Accuracy For Large-scale Speaker Verification (2021)9.76
• Neuralmultiling: A Novel Neural Architecture Search For Smartphone Based Multilingual Speaker Verification (2024)0.00
• Bayesian X-vector: Bayesian Neural Network Based X-vector System For Speaker Verification (2020)6.77
• An Improved Deep Neural Network For Modeling Speaker Characteristics At Different Temporal Scales (2020)6.34
• Generative X-vectors For Text-independent Speaker Verification (2018)7.16
• End-to-end Trainable Self-attentive Shallow Network For Text-independent Speaker Verification (2020)0.00
• Multi-task Learning With High-order Statistics For X-vector Based Text-independent Speaker Verification (2019)8.35
• Optimization Of The Area Under The ROC Curve Using Neural Network Supervectors For Text-dependent Speaker Verification (2019)10.21