Amazon introduced Echo, a new category of device designed around your voice. Echo was available on an invitation basis to customers who wanted to help shape the device as it evolved.
Echo uses on-device keyword spotting to detect the wake word. When Echo detects the wake word, it lights up and streams audio to the cloud, where it leverages the power of Amazon Web Services to recognize and respond to users’ request. Echo uses far-field voice recognition with an array of seven microphones to clearly hear users around the room. Advanced beam-forming technology combines the signals from the individual microphones to suppress noise, reverberation, and even competing speech. This audio signal is then used by our deep neural networks based speech recognition system trained on a large amount of far-field speech data to recognize your utterance from a distance. Enhanced noise cancellation allows customers to wake up the device even when it is playing loud music.
Echo has been fine-tuned to deliver crisp vocals with dynamic bass response. Its dual downward-firing speakers produce 360° omni-directional audio to fill the room with immersive sound. Plus, in addition to streaming music from the cloud, Echo is Bluetooth-enabled so customers can stream other popular music services like Spotify and iTunes from the phone or tablet.
Alexa, the brain behind Echo is built in the cloud, so it is always getting smarter. At launch, Echo introduced hands-free voice control for music (Amazon Music, Prime Music, iHeartRadio, and TuneIn), information from Wikipedia and the web, weather, timers and alarms, news, and shopping/to-do lists. Alexa has added dozens of new features to expand its skillset, gotten better at answering all types of questions, and improved accuracy and speech recognition.In addition, developers have been using a private beta of a free SDK to build new capabilities and skills for Alexa, which will start rolling out later.