Predicting Entity Popularity to Improve Spoken Entity Recognition by Virtual Assistants
This work addresses the challenge of recognizing trending entities in spoken queries for virtual assistant users, but it is incremental as it builds on existing ASR methods.
The paper tackled the problem of improving spoken entity recognition for virtual assistants by predicting which entities will become popular, resulting in a 20% relative reduction in errors on emerging entity name utterances.
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% relative reduction in errors on emerging entity name utterances without degrading the overall recognition quality of the system.