Predicting Entity Popularity to Improve Spoken Entity Recognition by Virtual Assistants

05/26/2020
by   Christophe Van Gysel, et al.
0

We focus on improving the effectiveness of a Virtual Assistant (VA) in recognizing emerging entities in spoken queries. We introduce a method that uses historical user interactions to forecast which entities will gain in popularity and become trending, and it subsequently integrates the predictions within the Automated Speech Recognition (ASR) component of the VA. Experiments show that our proposed approach results in a 20 on emerging entity name utterances without degrading the overall recognition quality of the system.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset