Introduction

Welcome to my weekly report documenting my journey during Google Summer of Code 2023 with the Linux Foundation! In this project, I am working on enhancing the existing speech-to-text feature of Automotive Grade Linux (AGL) by introducing a Natural Language Intent engine and implementing software daemons/controllers to execute the extracted intent. This endeavor aims to significantly improve the user experience and functionality of the speech-to-text feature in automotive environments. Throughout this report, I will share my progress, challenges faced, and achievements made as I contribute to the development of AGL and pave the way for more intuitive and intelligent voice interactions in automobiles.

Summary of the week

This week was marked by substantial progress as I focused on enhancing the NLU system's capabilities. Notably, I successfully crafted a custom dataset and trained an NLU model on RASA, covering a range of intents critical to the project. Moreover, I established a recipe for the RASA model, ensuring its seamless local integration into the target machine.

Tasks completed

• Crafted a custom dataset and trained an NLU model on RASA, encompassing essential intents like:
  • Dashboard Turn Signal
  • HVAC Temperature
  • HVAC Fan Speed
  • Media Player (Play, Pause, Prev, Next)
  • Navigation (To/Stop)
• Created a RASA model recipe, enabling the local deployment of the model on the target machine. This step streamlines the integration process and promotes efficient functionality.

The above new recipes have been incorporated into the existing meta-offline-voice-agent. You can find the RASA dataset and model files here.

Tasks leftover

No tasks were leftover this week.

Next steps

In the upcoming week, I have outlined the following tasks to be completed:

• Upload the RASA work to Gerrit.
• Extend the existing GRPC Server to effectively parse and execute intents from commands.

Conclusion

Overall, this week was productive, and I am satisfied with the progress made in achieving the goals outlined for the week. I am excited to continue my GSoC journey and further enhance the speech-to-text feature in Automotive Grade Linux.

Resources

There were no resources found attached to this post.