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 productive and marked significant progress in my GSoC project. I focused on optimizing the existing Natural Language Understanding (NLU) model by incorporating a navigation intent, which will enhance the system's ability to understand and respond to navigation-related queries. Additionally, I successfully developed a recipe to package the NLU model locally, ensuring seamless integration into the target system. To facilitate collaboration and code review, I uploaded all my current work to Gerrit as a patch set.

Tasks completed

• Integrated navigation intent into the existing NLU model, this enhanced the capability of the model to understand user queries related to navigation.
• Created a recipe that enables packaging the model locally into the target system. This packaging process streamlines the integration.
• Uploaded all the completed work as a patch set to Gerrit. This allows others to provide feedback, suggest improvements, and maintain a clear record of the project's progress.

The uploaded patch set on Gerrit can be found here.

Tasks leftover

The following tasks were leftover this week:

• SciPy and OpenBlas linking errors need to be resolved.

Next steps

• Create Software Controllers/Daemons: To execute commands based on user interactions, I will start working on developing Software Controllers or Daemons. These components will enable the system to perform various actions based on the user's intent, expanding the functionality of the overall system.
• Complete building of RASA: As part of the project, I will finalize the building process of RASA, an open-source machine learning framework for dialogue systems.

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.