1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. High-Accuracy And Low-Latency Speech Recognition With Two-Head Contextual Layer Trajectory Lstm Model

High-Accuracy And Low-Latency Speech Recognition With Two-Head Contextual Layer Trajectory Lstm Model

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion, we argue that su

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

Purchase

Videos in this product

High-Accuracy And Low-Latency Speech Recognition With Two-Head Contextual Layer Trajectory Lstm Model

00:14:32

2 views

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion, we argue that su