In this third and final part of the AoT blog series, we’ll take a look at some of the recent innovations that are finally bringing voice-based human/machine interfaces (HMIs) to the majority of consumer products.   While there’s been continual improvement in cloud-based technologies like automatic speech recognition (ASR) and natural language understanding (NLU), it’s largely been “edge-based” innovations that have knocked down the final barriers to the spread of voice-based HMIs. 

This is the first of a three-part blog series that explores the role that audio plays in our evolving relationship with machines  

San Jose and Santa Clara, CA – February 25, 2019 – DSP Group, Inc., a global leader in wireless chipsets for a wide range of smart-enabled devices, and DSP Concepts, Inc., a developer of embedded audio processing solutions, have announced that DSP Group’s DBMD7 line of floating-point audio processing chips will incorporate TalkTo™, DSP Concepts’ new audio front end technology for voice-controlled systems.

Comparing today’s car audio systems to those of 10 years ago is like comparing an iPad to a 1980s TV: They perform some of the same functions, but the modern product is vastly more capable and complex. Not only does a modern car audio system play radio, it must accommodate multiple sources (Bluetooth, USB sticks, analog inputs and CDs), and separate the driver’s voice from road and engine noise for phone calls and voice commands. It may have to generate warning sounds for pedestrians, and synthesize engine sounds to enhance the driving experience.