An End-to-End Architecture for Keyword Spotting and Voice Activity Detection
This enables efficient deployment of voice activity detection with no extra memory or maintenance, benefiting applications like voice assistants.
The authors tackled the problem of performing both keyword spotting and voice activity detection with a single neural network, achieving high accuracy on both tasks without retraining or aligned data.
We propose a single neural network architecture for two tasks: on-line keyword spotting and voice activity detection. We develop novel inference algorithms for an end-to-end Recurrent Neural Network trained with the Connectionist Temporal Classification loss function which allow our model to achieve high accuracy on both keyword spotting and voice activity detection without retraining. In contrast to prior voice activity detection models, our architecture does not require aligned training data and uses the same parameters as the keyword spotting model. This allows us to deploy a high quality voice activity detector with no additional memory or maintenance requirements.