Microsoft’s latest patent lets you issue voice commands silently

[The AchieVer]

The voice commands that many of us issue on a daily basis have become akin to second nature when speaking to Alexa on an Echo speaker, Google Assistant on a smartphone, or Siri on a smartwatch; however, voice commands can also be invasive within specific environments. You may not want to have to blurt out voice commands when you are having a party at your house or when you are out in public, but Microsoft might have the solution — a new way to issue voice commands by barely speaking at all.

 

A new patent filed by the company showcases what Microsoft is calling Silent Voice Input — a new method of communicating with our digital devices using voice but also spares us the social embarrassment of issuing voice commands loudly in public settings. The patent itself focuses on a small acoustic device that uses a user’s breath to determine speech; the device detects the airflow from a users month when breathing-in in an attempt to understand language.

“Although performance of voice input has been greatly improved, the voice input is still rarely used in public spaces, such as office or even homes. This is mainly because the voice leakage could disturb and even annoy surrounding people in quiet environment. On the other hand, there is still a risk of scattering private information to unintended audiences. These are not technical issues but social issues. Hence there is no easy fix even if voice recognition system performance is greatly improved.”

Unlike typical speech where an individual exhales air, speaking at a very low volume is accomplished by breathing inward, also known as ingressive breathing. Microsoft believes this difference is the key to better understanding speech at an extremely low volume. Patent imagery shows the device flush against a user’s nose as voice commands are issued in order to capture every minute movement of air.

 

In regard to usability, Microsoft’s patents showcase the technology being used in a stand-alone microphone of sorts, in addition to a smartwatch, smart ring, smartphone, headphones, and what appears to be a remote controller. The patent takes the time to note how the new invention can be implemented into a variety of devices, providing a more comfortable voice issuing experience in different settings. Whether Microsoft will actually implement the technology is yet to be seen, but may provide a more socially acceptable method for issuing voice commands on the go.

 

 

Microsoft patents technology that uses ingressive airflow for AI voice commands

Soon we could be whispering sweet nothings to Cortana

 

What just happened? Microsoft has filed a patent for technology that suggests users of voice assistants whisper commands while inhaling. The idea seems to be an attempt to make voice input more discrete, but does it? 

Several companies have been pursuing efforts to put people more at ease when speaking to their voice assistants in public. Google has worked considerably on making its AI more natural conversationally. Another company called Furhat Robotics thinks that giving voice assistants a face will make people more comfortable. Regardless of the method of getting there, most firms are looking at ways to encourage people to be more overt using AI in public.

 

Microsoft, on the contrary, seems to be moving in the opposite direction. According to a patent filed by the Redmond-based tech giant, ingressive airflow whispering is the answer. The suggestion is that users could whisper to their voice assistants thus making it less obvious they are using an AI. Only instead of whispering normally, the user would whisper while inhaling.

The reason for using ingressive airflow is that it causes less distortion for the microphone. Unfortunately, the mic must be placed very close to the mouth for it to pick up the commands. The design calls for the placement of the pick-up device to be within two millimeters.

The filing shows several types of devices that could be embedded with the input technology including smartwatches, rings, TV remotes, and small handheld microphones. However, none of these designs seem all that discrete.

It is debatable whether someone would feel more or less comfortable holding their watch right up to their mouth rather than just issuing an audible verbal command. Alternatively, it could be useful for times when normal voice levels are not quite appropriate, like when others are sleeping.

 

Microsoft has not announced any devices using the technology, and as a patent, there is no guarantee that it will ever come to market. If it does, I’m not sure I’d be one to embrace it. I’m quite comfortable remaining a closet user.

 

 

Source

 

Source