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 enhancing the Natural Language Understanding (NLU) system. I successfully completed the build of RASA by adding recipes for all its dependencies. Additionally, I optimized the existing NLU model to improve its inference capabilities, enhancing the system's ability to understand and respond to user queries more accurately.

Tasks completed

• Successfully built RASA by incorporating recipes for all its dependencies. The seamless build process of RASA paves the way for efficient model training and deployment. Following new recipes were added:
  • python3-aio-pika_8.2.3
  • python3-aiogram_2.25.1
  • python3-aiormq_6.4.2
  • python3-jsonpickle_3.0.1
  • python3-magic-filter_1.0.10
  • python3-pamqp_3.2.1
  • python3-pydantic_1.10.9
  • python3-typing-utils_0.1.0
  • python3-tensorflow (loaded as a seperate layer) (source)
• Enhanced the performance of the existing NLU model by improving dataset.

The above new recipes have been incorporated into the existing meta-offline-voice-agent.

Tasks leftover

No tasks were leftover this week.

Next steps

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

• Test RASA on target: Verify the successful integration of RASA and its dependencies by conducting comprehensive testing on the target machine.
• Explore RASA documentation: Delve into the RASA documentation to gain a deep understanding of the model training process. Familiarize with the necessary steps and best practices to effectively train the NLU model.
• Integrate Tensorflow into existing layer: Work on integrating Tensorflow into the existing meta-offline-voice-agent layer.

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.