1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Joint Phoneme-Grapheme Model For End-To-End Speech Recognition

Joint Phoneme-Grapheme Model For End-To-End Speech Recognition

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

This paper proposes methods to improve a commonly used end-to-end speech recognition model, Listen-Attend-Spell (LAS). The methods we proposed use multi-task learning to improve generalization of the model by leveraging information from multiple labels. T

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

Purchase

Videos in this product

Joint Phoneme-Grapheme Model For End-To-End Speech Recognition

00:14:05

0 views

This paper proposes methods to improve a commonly used end-to-end speech recognition model, Listen-Attend-Spell (LAS). The methods we proposed use multi-task learning to improve generalization of the model by leveraging information from multiple labels. T