Neuromorphic Audio Front-End

µWatts Voice & Sound Classification

with WhisperExtractor

WhisperExtractor is a disruptive technology addressing a major challenge in the voice-user interaction space – low power consumption.

With the increasing adoption of voice user interfaces in everyday objects, it has become critical to have efficient and low-power solutions for voice processing. Conventional digital signal processing methods to process MFCC require a significant amount of energy to convert analog signals to digital and perform signal processing calculations, making it difficult to implement always-on voice listening without draining the battery.

voice user interface

32 kHz RC Clock

Always on domain friendly.

Only 7 µWatts

Near-zero power consumption

Seamless Integration

No software required
Evaluation kit available

Up to 99% Energy Saving while Maintaining Inference Accuracy

Google Speech Command (20 words) - accuracy

Chinese KWS (25 words) - accuracy

Benefits

With its mixed-signal architecture, the WhisperExtractor is able to efficiently extract the Mel Frequency Cepstrum Coefficients (MFCC) needed for voice processing like you would usually do on a DSP. The output data of the WhisperExtractor is fully compatible with modern machine learning models and accelerators, including CNNs and RNNs.

This means that it is a versatile solution that can be easily integrated into a wide range of applications, from smart home devices to wearables and beyond.

  • Revolutionary technology in voice interaction.
  • Provides low-power voice processing and always-on listening.
  • Unleashes a world of possibilities for developers and manufacturers of innovative products.
  • A must-have solution for revolutionizing the voice user experience and staying ahead of the competition.

Applications with Power-Constrained VUI

Smart DMIC

A Digital Microphone (DMIC) for an integrated chip is a microphone that converts sound directly into a digital signal, using an analog-to-digital converter (ADC) integrated within the microphone itself.

Hearables

Hearables devices, like True Wireless Stereo (TWS) earbuds, hearing aids, and Over-The-Counter (OTC) hearing devices, are MCU-based in-ear devices.

Smart Speaker

A smart speaker in the context of semiconductors is an advanced audio device equipped with integrated circuits (ICs) that enable voice recognition, wireless connectivity, and interaction with other smart home devices.

IoT

IoT (Internet of Things) devices are smart, interconnected physical objects that collect, exchange, and process data through the internet.

Need to Discuss about Your Project?