An End-to-End Architecture for Keyword Spotting and Voice Activity Detection

@article{Lengerich2016AnEA,
  title={An End-to-End Architecture for Keyword Spotting and Voice Activity Detection},
  author={Christopher T. Lengerich and Awni Y. Hannun},
  journal={CoRR},
  year={2016},
  volume={abs/1611.09405}
}
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… CONTINUE READING
Tweets
This paper has been referenced on Twitter 34 times. VIEW TWEETS

References

Publications referenced by this paper.
Showing 1-10 of 11 references