Bayesian neural network language modeling for speech recognition

• المؤلفون الرئيسيون: Xue, Boyang, Hu, Shoukang, Xu, Junhao, Geng, Mengzhe, Liu, Xunying, Meng, Helen
• مؤلفون آخرون: School of Computer Science and Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2023
• الموضوعات: Engineering::Computer science and engineering; Bayesian Learning; Model Uncertainty
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/164438

State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. They are prone to overfitting and poor generalization when given limited training data. To this end, an overarching full B...