A Comparison of Streaming Models and Data Augmentation Methods for Robust Speech Recognition
2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)（2021）
关键词
speech recognition,Monotonic Chunkwise Attention (MoChA),RNN transducer (RNN-T),Vocal Tract Length Perturbation (VTLP),acoustic simulator,SpecAugment
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要