Knowles speeds up voice integration for Bluetooth devices

2 mins read

Knowles has unveiled the AISonic Bluetooth Standard Solution, a complete development solution designed to enable fast and easy voice integration into Bluetooth devices.

The development kit enables OEM and ODMs to build voice-activated calling, control, and far-field speech recognition capabilities into Bluetooth devices, including smart speakers, smart home locks, connected light switches, wearables and in-vehicle voice assistants.

The AISonic Bluetooth Standard Solution is one development package that is available under Knowles’ new line of reference solutions for voice activation, control, and contextual audio processing for TVs, portable speakers, soundbars, whitegoods, and a wide range of IoT electronics, known as Knowles Industry Standard Solutions.

The kit is built upon Knowles' AISonic Audio Edge Processor IA8201, which combines high performance with low power consumption to enable wake-on-voice functionality in small, battery-operated devices.

“The demand for voice control in all aspects of our lives is growing and becoming commonplace. But the market is fragmented, and with more connected devices coming to market it has become increasingly difficult to quickly integrate voice capabilities that work seamlessly,” said Vikram Shrivastava, senior director, IoT Marketing at Knowles. “Device manufacturers need high-quality, broad market development solutions to bring these capabilities to market quickly and scale to keep up with the fast-evolving way that we are living, working, and communicating. We’ve leveraged Knowles’ audio and voice integration expertise to create a powerful suite of standard solutions for different applications to make it easier for manufacturers to quickly and efficiently add speech recognition and voice capabilities to devices and get to market in a fraction of the time.”

The kit features an IA8201 reference board accompanied with an API supporting integration with Bluetooth chipsets having an embedded MCU running an RTOS, and system firmware release configured to support sensors and pre-integrated microphones from Knowles to enable the highest quality audio capture. The solution will help partners to scale further in developing AWS-AVS, Alexa Auto and AVS-AMA solutions on several Bluetooth and embedded MCU platforms.

The AISonic Bluetooth Standard Solution also includes algorithms for an Audio Front End suitable for use with many voice assistants or cloud-based ASR APIs. The Knowles OpenDSP partner program allows algorithm developers to provide libraries for a Beam Former, omnidirectional voice capture, AEC to sort voice commands from background to meet the stringent false wake standard of AVS.

Retune DSP is part of the Knowles OpenDSP ecosystem and has ported its voice-control solutions, VoiceSpot and VoiceSeeker to the IA8201.

VoiceSpot, an ultracompact wake word engine, enables voice-wake on memory-constrained, always-on, battery operated edge devices, and is Amazon-certified. VoiceSeeker is Retune’s multi-microphone audio front-end preprocessing solution capable for far-field voice control applications.

In addition, Retune’s Conversa two-way voice communication software solution enables the IA8201 on a number of high-performance Bluetooth speakerphones and headphones