Automatic Speech Recognition System Considerations for the Autonomous Vehicle 2019-01-0861
Automatic Speech Recognition (ASR) and Hands Free Calling (HFC) capabilities have become prominent in the automotive industry, with most new vehicle sales equipped with some level of ASR system. With the common use of mobile personal assistants and smartphones with Bluetooth capability, customer expectations for built-in ASR and HFC systems have increased significantly.
With the advent of the Autonomous Vehicle, the philosophy of customer interaction with the ASR system carried over from the traditional vehicle must be reconsidered. Now the voice-to-ASR system needs to be capable of serving a passenger in any seat of the car. These shifts in focus require changes to the microphone selection and placement to serve the entire vehicle.
Further complicating the scenario are new sources of sound that are specific to the Autonomous Vehicle. Hardware mounted on the roof that are used to support cameras and LIDAR sensors, and mechanisms meant to keep that hardware clean and functioning, add even further noise contamination to the voice interaction.
In this paper, we consider the complications on picking up the intended customer’s voice, when they are no longer bound to the traditional front left “driver’s” seat. Considerations are made to the possibilities of new microphone construction and layouts to provide coverage for all potential passengers, and cost-efficient minimal microphone packages are discussed. Additionally, if a “wake up word” is enabled to interact with the car’s digital assistant, instead of a plurality of Push to Talk (PTT) buttons for every seat, we discuss how the multiple microphone’s geometric placements may be leveraged to identify and focus further ASR interactions with the specific seat issuing the command.