Artificial Passenger - Speech Recognition

Speech Recognition

The speech recognition process relies on three steps. The front-end filters out any unwanted noise such as noise from the car, background music, or background passengers. It gets rid of all low energy and high variability signal being recognized. The labeler breaks apart the speech and searches in a data base to recognize what is being said. It starts broad by seeing what subject the driver is speaking of. Then goes into more details of what the driver is truly asking. The decoder next takes all this information and formulates a response to the driver. IBM states through much experimentation that the speech recognition is very accurate but the process has not fully been refined and still has kinks with in it.

The main part of the Artificial Passenger is the Disruptive Speech Recognition. This technology keeps a conversation with the driver and analyzes what the driver is saying and how s/he is saying it. It can recognize fluctuations in the driver’s voice to determine if the driver is sleepy, upset, or in a good mood through different vibration patterns in the driver’s speech. It also record the time it takes for a driver to respond in the conversation and from that determine if the driver is nodding off or being distracted by something.