Audio Intelligence at the Edge

Knowles is the leader in audio machine learning at the edge, redefining the audio experience in next generation devices. We offer a range of MEMS microphones, SmartMics with integrated DSPs and high-performance audio edge processors to meet diverse audio and voice input requirements for a range of smart phones platforms, IoT devices and headphones and earbuds.

smart-home-system-on-mobile-phone-with-background

Smarter Voice-Activated Smartphones

Serious-sports-tracking

Accurate Voice-Controlled Fitness Technology

smart-fridge

Responsive Intelligent Appliances

Privacy-Enabled Smart Speakers

Broken-glass-light-reflection-on-a-broken-window

Accurate Acoustic Event Detection

Knowles AISonic Audio Edge Processors

We have the most extensible family of audio processors, adaptable across any form factor. The Knowles AISonic™ Audio Edge Processors are optimized for machine learning, allowing for high compute and low power operation for voice activation, hands-free control and contextual audio processing in a range of mobile devices, TWS headsets, portable speakers, TVs and other IoT devices.

Knowles AISonic™ IA8201: Dual Core

The AISonic IA8201 is the industry’s first mobile-centric audio edge processor specifically designed for advanced audio and machine learning applications, enabling power-efficient intelligence and privacy at the edge. It offers robust voice activation and multi-microphone audio processing with the compute power to perform advanced audio output, context awareness and gesture control for today’s most advanced consumer electronics, optimized for power-sensitive applications.

The IA8201 includes a high compute 128-bit core (DMX) with Knowles proprietary instruction set and a Tensilica HiFi3 core (HMD), both with Knowles audio enhancements. The DMX is a 4-way floating-point SIMD processor targeted towards efficient, high-performance computing (e.g. beam-forming, barge-in, AEC), while the HMD is targeted towards efficient, low-power, wake-on-voice applications with a two-way floating-point SIMD processor. Both cores contain dedicated accelerators for FFT, peak finding and DNNs.

A rich set of audio, and general purpose high speed interfaces enable flexible interfacing with digital microphones, other sensors, and a host for further processing. 1MB of user RAM enables storage of multiple algorithms and voice keywords.

Product Features

Multi-Core: HemiDelta for low power and DeltaMax optimized for audio compute and machine learning

4 mics, multiple high speed interfaces and GPIOs

Memory: 1MB user available RAM, with support for dynamic plugins

Audio Interfaces: 4x PDM in, Stereo PDM out, 3x I2S/TDM (4ch in/out)

Ports: 2x I2C, 2x SPI, 2 x UART, 24 GPIOs w/interrupts

Knowles Block Diagram9.27.19

Knowles AISonic™ IA8508: Quad Core

The AISonic IA8508 is a highly flexible, quad-core audio edge processor with 4MB of user memory, which allows for larger models and concurrent processing of multiple, high-performance algorithms in applications requiring intensive edge processing and privacy. All of this is designed with low-power in mind for audio context aware and and voice assistant applications.

The IA8508 has four cores, the HMD, the DMX, a low latency SSP, and an Arm Cortex M4 for control. The SSP is a 256-bit single-cycle processor targeted toward low latency computing and hardware acceleration of asynchronous sample rate conversion (ASRC).

Open DSP, available on all of our edge processors, provides a robust platform for customer or third-party solutions. The SDK with Knowles and Xtensa HiFi 3 instruction sets allows for extensive voice and audio processing, capable voice user interfaces, sensor fusion with audio, ambient sound detection, and much more.

Product Features

8 PDM microphone interfaces

Three heterogeneous Tensilica-based, audio-centric DSP cores and an Arm Cortex M4 for maximum design flexibility

All four cores can simultaneously run high performance floating-point algorithms leveraging the IA8508’s 5.7MB of RAM. The multicore audio processor can be configured into an ultra-low power system targeting power-conscious designs

Audio Interfaces: 4x PDM in, Stereo PDM out, 3x I2S/TDM (4ch in/out)

Low-latency utilizing a single sample processor (SSP) core for real-time processing for audio applications such as ANC (active noise cancellation) or asynchronous sample rate conversions of various audio sources

Knowles AISonic SmartMics

Our low-power Knowles AISonic family of SmartMics are adaptable across form factors in Mobile, TWS and IoT, delivering better audio understanding across a wide range of devices with a small footprint. Processing at the edge, the SmartMic provides wake-on-voice capabilities with lower power consumption, and privacy without compromising performance.

Knowles AISonic SmartMics

The IA61x family of “wake-on-voice” SmartMics (microphones), feature a 43MHz Tensilica audio-optimized DSP, and Knowles’ high performance acoustic SiSonic™ MEMS technology in a single, miniature, microphone package. The integrated programmable DSP is made available to third-party algorithms, enabling full customization (IA611). The solution pushes the system performance to ultra-low power with its custom core design and optimized instruction set. It accelerates time-to-market with its complete hardware, software, firmware, code and tools package.

Product Features

High-accuracy, low-power voice wake and Voice ID keyword recognition to wake up any system from a trigger phrase

Onboard buffer enables seamless voice wake operation

Ultra-low power “always on” Acoustic Activity Detector (AAD)

Beamforming for enhanced sound quality

Open Developer Platform with SDK

High Performance SiSonic MEMS with ±1 dB matched sensitivity, 65 dB SNR and 135 dB SPL Acoustic Overload Point

Application Memory Size: 168KB

IA610 available in bottom port SPH 3.50 x 2.65 x 0.98 mm package, and IA611 available in open DSP top port SPK 4 x 3 x 1.2 mm package

Knowles AISonic™ SmartMic Headset Development Kit for Amazon AVS

The first development kit qualified by Amazon for AVS for hands-free, voice-activated low-power headphones, headsets and earbuds for eliminating the need for push-to-activate.

The Knowles AISonic™ SmartMic Headset Development Kit for Amazon Alexa Voice Service (AVS) is the first development kit qualified by Amazon for AVS that enables OEMs and ODMs to build Bluetooth headphones, headsets and true wireless earbuds enable voice activation and eliminate the need for push-to-activate—allowing consumers to use their headsets to talk, hands-free, directly to Alexa supporting all Alexa capabilities. The development kit is fully compliant with Amazon’s Alexa Mobile Accessory (AMA) protocol for Bluetooth accessories and supports the industry’s lowest power and wake-on-voice capability for Alexa ear-worn devices.

knowleswebsite-images

Smartphones

Knowles is the world leader in designing audio solutions for smartphone platforms. Enabling mobile machine learning at the edge, we address the rapidly growing demands for voice interface, privacy and better understanding in noisy environments.

Knowles offers a range of MEMS microphones, SmartMics with integrated DSPs and high-performance MultiMic stand-alone audio processors to meet diverse audio and voice input requirements for a range of mobile phones and platforms. Knowles AISonic™ Audio Edge Processors offer very low power, wake-on-voice near and far-field wake-word detection, voice quality enhancement and sensor signal processing.

Voice Wake

Voice Wake

  • Enable wake-on-voice voice trigger detection with an audio DSP integrated microphone package
  • High accuracy detection
  • As low as 2mW average power
  • Microphone plus DSP in a tiny 9.3mm² footprint

Beyond Voice

Beyond Voice

  • Expand beyond voice input with low power, high compute, and large memory audio processors
  • Choose between flexible 1MB and 4MB memory options for beyond voice applications

AI, Machine Learning

AI, Machine Learning

  • Take advantage of high compute machine learning with DNN accelerators
  • Knowles AISonic Audio Edge Processor platforms machine learning tasks 10 times more efficiently than competition.

Context Aware

Context Aware

  • Detect trigger words, detect context, process gestures
  • Aggregate sensor inputs to determine user physical context
  • Process ultrasonic inputs to enable proximity sensing, gesture detection

IoT

Leveraging our experience in MEMS microphones, SmartMics, hearing health, balanced armatures and audio edge processors, Knowles delivers new capabilities such as market leading low power, wake-on- voice UI and advanced audio processing technology for a range of ear worn consumer devices that delight and empower users, such as advanced audio augmented reality and market leading voice UI technology.

Applying leading edge capabilities for optimal machine learning performance, our AISonic™Audio Edge Processors are designed to provide wake-on-voice processing features that respond to the users voice, hands-free whenever needed. Pioneering low power audio processors are paired with optimized MEMS microphones to set new standards of performance and innovation in next generation hearables.

Knowles enables headphones and true wireless earbuds with a richer audio experience and seamless interaction with intelligent voice assistants.

Smart Speakers

Smart Speakers

  • Stream audio services and use an AI voice assistant for an interactive experience that is growing everyday with cloud services
  • Support for all major cloud ASRs (automatic speech recognition)
  • Best-in-class far-field voice processing
  • Lowest power consumption for portability

Smart Screens

Smart Screens

  • Embedded in a range of voice devices, a cloud ASR gets deeply integrated into our lifestyle throughout the home
  • Visual interactivity
  • Voice conferencing
  • Voice control and search with TV viewing

Smart Homes

Smart Homes

  • Seamlessly automate with voice comfort, luxury and security
  • Lights, thermostats and threat/intrusion detection
  • Voice throughout the entire home manages energy, cameras and content distribution
  • Control any device from anywhere within the home

Headphones and Earbuds

Leveraging our experience in MEMS microphones, SmartMics, hearing health, balanced armatures and audio edge processors, Knowles delivers new capabilities such as market leading low power, wake-on- voice UI and advanced audio processing technology for a range of ear worn consumer devices that delight and empower users, such as advanced audio augmented reality and market leading voice UI technology.

Applying leading edge capabilities for optimal machine learning performance, our AISonic™Audio Edge Processors are designed to provide wake-on-voice processing features that respond to the users voice, hands-free whenever needed. Pioneering low power audio processors are paired with optimized MEMS microphones to set new standards of performance and innovation in next generation hearables.

Knowles enables headphones and true wireless earbuds with a richer audio experience and seamless interaction with intelligent voice assistants.

Voice Wake

Voice Wake

  • Wake-on-Voice Triggering
  • Premium voice wake performance
  • Lowest power (as low as 2 mW)

Noise Reduction

Noise Reduction

  • Minimizing Noise for Enhanced Audio Quality
  • Beam forming and noise source cancellation
  • Wind noise reduction

Context Aware

Context Aware

  • Detecting Acoustic Environments & Events
  • Machine learning for reliable detection of targeted events
  • Enables products that tune themselves for the listener’s current audio environment

HiFi Audio

HiFi Audio

  • Advanced Audio Output Processing & Premium Sound Reproduction
  • Hi-Res sound reproduction in a tiny unit designed for in-ear form factors
  • Audio signal processing delivers optimal sound for the best listening experience

AI & Machine Learning

AI & Machine Learning

  • Processing Audio Data to Determine Context & Enhance User Experience
  • DNN-optimized instruction set & processors
  • Natural language understanding

Hearing Enhancement

Hearing Enhancement

  • Advanced Hearing Capabilities for Consumers in Challenging Environments
  • High sensitivity microphones & advanced audio processing for new market categories
  • Proven sound reproduction technology, pioneered for high-end medical devices, applied to consumer applications

News

For more information, visit the Intelligent Audio Portal