iM401

iM401
Smart Microphone Processor

Category: Smart Microphone Processor
Application: Mobile, Consumer and IoT

Introduction

The iM401D/iM401DF is a mini DSP (digital signal processor) designed for voice trigger processing. The iM401D is an all-digital product that supports digital microphone input. The iM401D is built to support not only voice trigger and key phrase detection but also one shot command recognition with 3rd party algorithms.

  • Voice trigger activation device

  • Support for Sensory and iFlytek voice trigger and key phrase detection software

  • All digital operation for low power

  • Special low power voice/sound detection modes

  • User defined key word detection with Sensory solution

  • Support for multiple different languages and dialects

Summary of Benefits

  • Low power operation during silence and voice activity detection

  • Option for very low power Digital Voice Activity Detection

  • Selectable thresholds for false detection and false recognition rate balancing

  • OEM defined trigger words and phrases supported

  • Hands free wake-up of battery powered devices with extremely low power

Applications

  • Voice Wake-up for mobile and other consumer devices

Features

  • Tensilica HiFi-mini DSP Core

  • Programmable operation speed (1~24MHz)

  • 72KB DSP Memory size (24KB Instruction RAM and 48KB Data RAM)

  • Additional 64KB memory built in for voice buffer, can also be used as runtime program memory

  • Support Slave Mode I2C Control Interface (Up to 1MHz clock)

  • Power management and enhanced power saving

  • Stereo digital microphone inputs

  • Digital microphone clock speed from 0.512MHz to 3.25MHz (0.512 MHz steps)

  • Interrupt (IRQ) output to indicate a voice wake up event to host chip

  • 1MHz RC clock and PLL with clock calibration in power saving mode

  • Single digital power supply from 1.6V to 3.6V voltage

  • Available in 12 Pin DFN or 12 Pin WLCSP packages (DFN: 3 x 3 x 0.85 mm, 0.45 mm ball pitch- WLCSP: 1.385 x 1.889 x 0.55 mm, 0.4 mm ball pitch)

Voice Wake-Up Features

  • Pre-trained trigger word support – multiple languages

  • User defined trigger word (with Sensory package)

  • Option for user defined trigger word or phrase

  • 2 to 3 second Voice Buffer capability

  • I2C Control Interface
    - Simple IRQ to wake up Application Processor