Intel and Amazon have announced a new partnership for creating a new developmental kit. This kit will allow developers to embed Amazon’s Alexa voice-control capabilities in third-party smart home devices. The device, known as the Intel Speech Enabling Developer Kit, provides an audio front-end solution and is claimed to be the first device to combine Alexa wake word detection and far-field voice processing on a single chip.
Intel’s Speech Enabling Developer Kit is designed to provide a complete audio front-end solution for far-field voice control. It includes algorithms that are designed for acoustic echo cancelation, noise reduction (to enable speech capture in noisy environment), beam forming and a custom wake-word engine tuned to Alexa. It also comes with Intel’s dual digital signal processor with inference engine and its eight-microphone circular array.
“There’s a lot of engineering involved in getting speech recognition at high degrees of speed and accuracy to deliver the best customer experiences,” said Miles Kingston, general manager of Intel’s smart-home group in a statement. “The Intel Speech Enabling Developer Kit is based on a new architecture that delivers high-quality far-field voice even in the most acoustically challenging environments.”
In January Amazon announced its strategy “Alexa everywhere,” which would enable it to partner with multiple companies and manufacturers to bring Alexa’s potential to numerous devices, including a series of smart TV’s from Chinese firm Tongfang Global, washing machines and DVRs. Now Alexa’s amalgamation with Intel’s developmental kit could make it much easier for manufacturers and innovators to build this technology in their devices.
“Natural language means machines need to clearly recognize and respond to user commands from a reasonable conversation distance,” Intel Product Marketing Manager Miles Kingston explained in a statement. “People speak and hear in 360 degrees, not just in a direct line of sight. A quality voice interaction means devices identify the speaker’s location, mitigate and suppress ambient noise, and understand spoken commands on the mics, even while playing music … as well as waking up when it hears the wake word.”