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

During this week, I made substantial progress in my GSoC project, focusing on optimizing the Natural Language Understanding (NLU) system. The key achievements for this week include successfully building Tensorflow by cloning it from the upstream master branch of OE and ensuring all missing dependencies were resolved. Additionally, I conducted rigorous testing of RASA on the target system and efficiently addressed any missing runtime dependencies, ensuring smooth functionality.

Tasks completed

• Completed the build of Tensorflow by cloning it from the upstream master branch of OE and resolving any missing dependencies. This step is crucial in preparing the NLU system for advanced model training and inference.
• Conducted testing of RASA on the target system and addressed any missing runtime dependencies. Ensuring that RASA works seamlessly on the target system is a critical milestone towards achieving a reliable and efficient NLU system.

Tasks leftover

No tasks were leftover this week.

Next steps

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

• Craft dataset and train an NLU model on RASA: This step will involve preparing a comprehensive dataset and using it to train the NLU model, which will significantly improve the system's understanding and responsiveness to user queries.
• Start working on the command execution: Developing the capability to execute commands based on user intent will bring practical utility to the NLU system, making it more versatile and user-friendly.

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.