1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Leveraging Unpaired Text Data For Training End-To-End Speech-To-Intent Systems

Leveraging Unpaired Text Data For Training End-To-End Speech-To-Intent Systems

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

Training an end-to-end (E2E) neural network speech-to-intent (S2I) system that directly extracts intents from speech requires large amounts of intent-labeled speech data, which is time consuming and expensive to collect. Initializing the S2I model with an

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

Purchase

Videos in this product

Leveraging Unpaired Text Data For Training End-To-End Speech-To-Intent Systems

00:14:00

0 views

Training an end-to-end (E2E) neural network speech-to-intent (S2I) system that directly extracts intents from speech requires large amounts of intent-labeled speech data, which is time consuming and expensive to collect. Initializing the S2I model with an