Speech Recognition and Understanding on Hardware-Accelerated DSP

Georg Stemmer, Munir Georges, Joachim Hofer, Piotr Rozen, Josef Bauer, Jakub Nowicki, Tobias Bocklet, Hannah R. Colett, Ohad Falik, Michael Deisher, Sylvia J. Downing


A smart home controller that responds to natural language input is demonstrated on an Intel embedded processor. This device contains two DSP cores and a neural network co-processor which share 4MB SRAM. An embedded configuration of the Intel RealSpeech speech recognizer and intent extraction engine runs on the DSP cores with neural network operations offloaded to the co-processor. The prototype demonstrates that continuous speech recognition and understanding is possible on hardware with very low power consumption. As an example application, control of lights in a home via natural language is shown. An Intel development kit is demonstrated together with a set of tools. Conference attendees are encouraged to interact with the demo and development system.


Cite as: Stemmer, G., Georges, M., Hofer, J., Rozen, P., Bauer, J., Nowicki, J., Bocklet, T., Colett, H.R., Falik, O., Deisher, M., Downing, S.J. (2017) Speech Recognition and Understanding on Hardware-Accelerated DSP. Proc. Interspeech 2017, 2036-2037.


@inproceedings{Stemmer2017,
  author={Georg Stemmer and Munir Georges and Joachim Hofer and Piotr Rozen and Josef Bauer and Jakub Nowicki and Tobias Bocklet and Hannah R. Colett and Ohad Falik and Michael Deisher and Sylvia J. Downing},
  title={Speech Recognition and Understanding on Hardware-Accelerated DSP},
  year=2017,
  booktitle={Proc. Interspeech 2017},
  pages={2036--2037}
}