Incorporating VAD into ASR System by Multi-task Learning

no code implementations • 2 Mar 2021 • Meng Li, Xia Yan, Feng Lin

When we use End-to-end automatic speech recognition (E2E-ASR) system for real-world applications, a voice activity detection (VAD) system is usually needed to improve the performance and to reduce the computational cost by discarding non-speech parts in the audio.

Action Detection Activity Detection +4

Understanding the Disharmony between Weight Normalization Family and Weight Decay: $ε-$shifted $L_2$ Regularizer

1 code implementation • 14 Nov 2019 • Li Xiang, Chen Shuo, Xia Yan, Yang Jian

These methods use standardization or normalization that changes the weight $\boldsymbol{W}$ to $\boldsymbol{W}'$, which makes $\boldsymbol{W}'$ independent to the magnitude of $\boldsymbol{W}$.