Search Results for author:
Found 2 papers, 0 papers with code
Adaptive Activation Network For Low Resource Multilingual Speech Recognition
The existing models mostly established a bottleneck (BN) layer by pre-training on a large source language, and transferring to the low resource target language.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
MLNET: An Adaptive Multiple Receptive-field Attention Neural Network for Voice Activity Detection
The MLNET leveraged multi-branches to extract multiple contextual speech information and investigated an effective attention block to weight the most crucial parts of the context for final classification.
