1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Learning Recurrent Neural Network Language Models With Context-Sensitive Label Smoothing For Automatic Speech Recognition

Learning Recurrent Neural Network Language Models With Context-Sensitive Label Smoothing For Automatic Speech Recognition

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

Recurrent neural network language models (RNNLMs) have become very successful in many natural language processing tasks. However, RNNLMs trained with a cross entropy loss function and hard output targets are prone to overfitting, which weakens the languag

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Learning Recurrent Neural Network Language Models With Context-Sensitive Label Smoothing For Automatic Speech Recognition

00:13:47

0 views

Recurrent neural network language models (RNNLMs) have become very successful in many natural language processing tasks. However, RNNLMs trained with a cross entropy loss function and hard output targets are prone to overfitting, which weakens the languag