The Amazon Echo is a smart speaker developed by amazon.com. The device consists of a 9.25-inch tall cylinder speaker with a 7-piece microphone array, a few speakers, and a small computer. When device responds to the name "Alexa", which is called its "wake word". The device is capable of voice interaction, music playback, making to-do lists, setting alarms, streaming podcasts, playing audiobooks, and providing weather, traffic, and other real time information. The device uses speech recognition to perform these tasks on command.
In default mode, the device continuously listens to all speech, constantly monitoring for the wake word "Alexa" to be spoken. The device also comes with a manually and voice-activated remote control, which can be used instead of the wake word. The remote control and wake word are two forms on input that the device utilizes. When you say the word "Alexa", the Echo immediately recognizes the word, and begins recording your voice. Once you finish speaking, the device sends the voice recording over the internet to amazon. The recording is then processed by a service called Alexa Voice Services (AVS). The AVS converts the recording into commands that it interprets. Those commands result in the device's output, whether it be playing music, telling the time, or providing traffic patterns.
For example, if you ask Alexa for the time, the Echo will send the voice recording to AVS. The AVS then interprets the message, and sends back an audio file of Alexa telling you the time, which the Echo plays back. Another example is if you asked Alexa to play the Lumineers, the AVS will search the music service that you set up for their music, then send a command back to the Echo that sets it playing the requested music.
The necessity of the computer behind this technology is obvious. Our voice, which is transmitted through the microphones, is our input mechanism. The Echo takes our request and processes the request using AVS, which produces commands for the Echo to follow. The Echo will then output its response to the commands through the speakers. Amazon has made listening to what you want, when you want it, an even easier, hands-off experience with the Echo.
References:
Great article! It was really interesting for me to read about the differences between how the amazon echo works and how Siri works since I wrote an article about that a couple of weeks ago. It is nice to read that even though interpetating voice recognition is complicated, it always goes back to an input and an output.
ReplyDeleteThis is really cool! I have never seen one of these, but I have seen the commercials and I didn't know it works completely like voice command. I guess that the real difference between the Echo and other popular voice activated programs is the wake work, which is really incredible. I wonder what else similar programs will be able to do in the future, like controlling the lights in the house, turning on the tv, etc with just voice activation.
ReplyDeleteHi,
ReplyDeleteYour article reminded of when I saw a person using this speaker at the University Help Desk and it was really cool. He was asking it the general knowledge questions as well and it was responding to all those question.