products header

earSmart's Auditory Intelligence Allows Us to Do More

The complex science of human hearing drives earSmart™ Advanced Voice technology, providing auditory intelligence that gives our processors more functionality and higher performance. Designed to work like the human ear, our voice processors instinctively distinguish and enhance sounds of interest, while suppressing noise, to deliver more clarity, and better-sounding voice and audio quality, dramatically improving the user experience with mobile phones or tablets.

Our system-on-chip earSmart voice processors are setting a new voice quality standard and positioning Advanced Voice technology as a “must have” feature for the latest mobile devices. earSmart Advanced Voice processors offer more consistency and positional robustness, and feature Audience’s high performance, low-power audio DSP core that delivers added computational capacity to enable the latest voice applications across mobile usage modes. They are also customizable, allowing device makers to tune the processor for a signature sound, plus highly scalable, supporting voice innovations today, and in the future.

earSmart voice technology is integrated in over 100 mobile handsets with leading device manufacturers and wireless operators, involving almost every new device architecture, form factor, operating system (OS), and network. We have experience integrating into systems that ship millions of units globally, and deliver a proven “whole product” solution, with software, tools, design collateral, and a global technical organization to support easy integration and rapid time-to-market.

  • 1
  • 2
  • 3
  • 4
  • 5
  • 6


Choose one of our products to learn more and see features and specifications.


eS515

  • Print

earSmart™ eS515 Smart Sound Processor

The earSmart eS515 is the world’s first Smart Sound Processor, integrating award-winning earSmart Advanced Voice technology with a high-performance, low-power audio codec for best-in-class voice and multimedia experience. With a suite of new features around communications, speech recognition and entertainment, the earSmart eS515 allows consumers to be heard, be understood and be there.





Be Heard | With Best in Class Voice Processing

The earSmart eS515 features 3rd generation Advanced Voice processing features. The earSmart eS515 delivers the world’s first true support of three-microphones, where all three are used simultaneously to gather more information about the user’s surroundings and deliver vastly improved voice quality, even when the user is in a noisy environment. The earSmart eS515 also features the world’s first implementation of de-reverberation technology for mobile devices, significantly reducing the echo effect heard in spaces such as conference rooms and hallways.





Be Understood | With Improved Automatic Speech Recognition Assist

ASR Assist technology directly addresses the challenge faced by many speech recognition applications today, namely their failure to recognize spoken words and complete assigned tasks because of disruptive background noise. The earSmart eS515 uses custom hardware-accelerated algorithms to isolate voice from surrounding environmental noise, dramatically improving the accuracy of speech-enabled applications such as voice search and speech to text. Mobile devices equipped with Audience ASR Assist technology deliver improved speech application reliability, accuracy and task completion – even in noisy, distracting environments.





Be There | With Enhanced Multimedia Capture and Playback

Mobile devices today are relied upon for media capture as much as they are for communication, and the desire for captured audio to be the same high definition (HD) quality as video has never been more apparent. The earSmart eS515 Smart Sound Processor features the world’s first two-microphone 48 KHz noise suppression implementation for recording clean, high definition audio. The earSmart eS515 also features Audio Zoom, the world’s first selective audio capture feature to be deployed for mobile devices, allowing users to dynamically switch between narrator and interview modes, capturing both voices with crystal clear accuracy while removing background noise.



The Science Behind the earSmart eS515 Smart Sound Processor

es515 Chip diagram

 

Product Highlights

Voice Features
  • Non-Stationary and Stationary Noise suppression (Close talk, Far talk)
  • ASR Assist mode
  • Audience Hi-Fi Voice, Voice Stretch and Acoustic Echo Cancellation
  • Automatic Gain Control, Voice Equalization, Post Equalization and Multiband Compressor
  • Narrowband (8kHz), Wideband (16kHz) and Super Wideband (24 kHz)signal processing
  • Transmit De-reverb

Audio Features
  • UI Tone Mixing, Audio Multiband Compressor (MBC), Parametric EQ and Stereo Widening
  • Dynamic Range Compressor (DRC)
  • Equalizer Engine and Virtual Bass Boost support (OpenSL ES1.1 compliant)
  • Configurable Beep Generator
  • Multimedia recording features
    • Audio Zoom directional sound capture modes for camcorder application
    • Enhanced Stereo Recording: Presets for optimized camcorder performance in multiple everyday, real-life environments
    • Stereo 2-Mic Stationary Noise Suppression

Key Device Features
  • Audience earSmart Voice Processing core
  • 4 High performance DACs with104dB dynamic range
  • 4.8 mW Stereo Playback at 48kHz
  • 1.1 W Stereo Class-D Speaker Driver
  • 30 mW Stereo Class-G Headphone Driver
  • 80 mW Earpiece Driver
  • 2 Line Output Drivers
  • 2 High performance 92dB SNR ADCs with Mic PGAs
  • 1 Auxiliary ADC for line input with PGA
  • SLIMbus Interface
  • Digital Audio Ports
    • 3 Master/Slave PCM/I2S ports
    • Supports 4 digital Mic inputs and 1 output
    • Up to 192kHz sample rates
  • I2C,UART, and SLIMbus Host Interfaces


Click to download the Product Brief (PDF)

eS325

  • Print

earSmart™ eS325 Advanced Voice Processor

The Audience earSmart eS325 Advanced Voice Processor features all the newest technologies necessary for the best-sounding voice experience on modern mobile devices, delivering innovations in real-time communications, speech recognition and media capture. The earSmart eS325 is the first Advanced Voice Processor to feature industry-first innovations such as: simultaneous three-microphone processing, optimized Automatic Speech Recognition, Mobile Audio Zoom, Super Wideband support for Voice over IP (VoIP) and Enhanced Stereo Recording. The earSmart eS325 also features Bandwidth Expansion (BWE) technology for a consistent, HD-quality voice call experience when moving between 3G and 4G networks, while also meeting the tighter latency requirements of the European HD Voice standard, ensuring reduced delay for more natural conversations.





Be Heard | With Best in Class Voice Processing

The earSmart eS325 features 3rd generation Advanced Voice processing features. The earSmart eS325 delivers the world’s first true support of three-microphones, where all three are used simultaneously to gather more information about the user’s surroundings and deliver vastly improved voice quality, even when the user is in a noisy environment. The earSmart eS325 also features the world’s first implementation of de-reverberation technology for mobile devices, significantly reducing the echo effect heard in spaces such as conference rooms and hallways.





Be Understood | With Improved Automatic Speech Recognition Assist

ASR Assist technology directly addresses the challenge faced by many speech recognition applications today, namely their failure to recognize spoken words and complete assigned tasks because of disruptive background noise. The earSmart eS325 uses custom hardware-accelerated algorithms to isolate voice from surrounding environmental noise, dramatically improving the accuracy of speech-enabled applications such as voice search and speech to text. Mobile devices equipped with Audience ASR Assist technology deliver improved speech application reliability, accuracy and task completion – even in noisy, distracting environments.





Be There | With Enhanced Multimedia Capture and Playback

Mobile devices today are relied upon for media capture as much as they are for communication, and the desire for captured audio to be the same high definition (HD) quality as video has never been more apparent. The earSmart eS325 Smart Sound Processor features the world’s first two-microphone 48 KHz noise suppression implementation for recording clean, high definition audio. The earSmart eS515 also features Audio Zoom, the world’s first selective audio capture feature to be deployed for mobile devices, allowing users to dynamically switch between narrator and interview modes, capturing both voices with crystal clear accuracy while removing background noise.



The Science Behind the earSmart eS325 Advanced Voice Processor

es515 Chip diagram

 

Product Highlights

Voice Features
  • Non-Stationary and Stationary Noise suppression (Close talk, Far talk)
  • ASR Assist mode
  • Audience Hi-Fi Voice, Voice Stretch and Acoustic Echo Cancellation
  • Automatic Gain Control, Voice Equalization, Post Equalization and Multiband Compressor
  • Narrowband (8kHz), Wideband (16kHz) and Super Wideband (24 kHz)signal processing
  • Transmit De-reverberation

Audio Features
  • UI Tone Mixing, Audio Multiband Compressor (MBC), Parametric EQ and Stereo Widening
  • Dynamic Range Compressor (DRC)
  • Equalizer Engine and Virtual Bass Boost support (OpenSL ES1.1 compliant)
  • Configurable Beep Generator
  • Multimedia recording features
    • Audio Zoom directional sound capture modes for camcorder application
    • Enhanced Stereo Recording: Presets for optimized camcorder performance in multiple everyday, real-life environments
    • Stereo 2-Mic Stationary Noise Suppression

Key Device Features
  • 3x3 mm footprint
  • 40nm process technology
  • Third Generation Audience earSmart Advanced Voice Processing core
  • SLIMbus Interface
    • 10 receive data ports and 6 transmit data ports.
    • Support for Isochronous, Pushed, and Pulled Transport Protocols
  • Digital Audio Ports
    • 3 Master/Slave PCM/I2S ports
    • Supports 4 digital Mic inputs and 1 output
    • Up to 192kHz sample rates
  • I2C,UART, and SLIMbus Host Interfaces


Click to download the Product Brief (PDF)

eS310

  • Print

earSmart™ eS310 Voice Processor

The earSmart™ eS310 voice processor builds on the feature-rich framework of the eS305 advanced voice processor with added analog interfaces to help reduce the overall system BOM cost. The eS310 is power efficient, easy to integrate and intelligently adapts to noisy environments to deliver clearer calls in video chats, VoIP and cell phone conversations.

 

Product Highlights

Powerful Processing

Featuring Audience's next-generation, high-performance custom digital signal processor (DSP) core, the eS310 system-on-chip provides advanced processing for:

  • Wideband and narrowband non-stationary noise suppression
  • Close-talk, both transmit and receive
  • Handheld speakerphone (HHS) mode
  • Acoustic echo cancellation (AEC)
  • Automatic receive voice equalization (VEQ) to boost voice above the ambient acoustic environment
  • Parametric equalizer for enhancing audio playback
  • Wideband HD voice listening experience over narrowband networks

Accessibility Features

To provide customization and personalization options for OEMs, the eS310 processor includes:

  • Personal Receiver Equalization -- to allow customers to select a receive frequency response that matches their hearing characteristic
  • Voice Stretch Mode – slows a calling party’s voice in real-time, retaining pitch accuracy, for improved comprehension during rapid conversations or for voice recording playback

Customization Features

To optimize performance, the eS310 processor includes:

  • A post-equalization (Post-EQ) filter for voice color tuning and to allow handset manufacturers to manage frequency response
  • A receive multi-band compander (MBC) to improve audio quality and offer speaker distortion compensation

Easy Integration

Enabling easy design-in, the eS310 processor includes:

  • Audience’s AuViD 2.0 graphical software application to support the design and integration process, featuring step-by-step visual design tools to efficiently tune the audio features of the eS310 processor and customize voice capabilities
  • Auto microphone calibration to eliminate costly testing and per-unit adjustments on the production line
  • Graphical filter design tools for easy customization of Post-EQ and MBC filter design

Efficient Platform

Designed for energy efficiency, the low-power, high performance chip is:

  • Packaged in a highly compact 3.5mm x 3.5mm, 49-pin BGA (0.4mm pitch).
  • Meets RoHS and Green requirements
  • Designed to fit any handset style or design configuration

Specifications

Power Supplies

  • LDO 1.8V; I/O: 3.3V~1.8V
  • Codec:  2.5V~3.3V

Host Interface

  • Up to 1Mbps I2C interface
  • Up to 3Mbps UART

Analog Audio Interface

  • Two analog microphone inputs
  • One analog auxiliary input
  • Two analog line driver outputs

Digital Audio Interface

  • Three I2S/PCM interfaces
  • Supports digital microphone input


Click to download the Product Brief (PDF)

eS305

  • Print

earSmart™ eS305 Voice Processor

The earSmart™ eS305 voice processor features innovations that deliver high-definition (HD) voice quality in tablets and mobile phones. With multiple digital interfaces, the eS305 processor is designed to integrate easily into tablet or a mobile phone architecture. The eS305 voice processor provides dramatic voice enhancement and wideband noise suppression delivering clear, life-like conversations for video chats, VoIP and phone calls over a broadband Wi-Fi® or mobile 4G wireless networks.

 

 

Product Highlights

Powerful Processing
  • Wideband and narrowband non-stationary noise suppression, both transmit and receive  
  • Handheld speakerphone (HHS) non-stationary noise suppression, transmit and receive
  • Acoustic echo cancellation (AEC)
  • Automatic receive voice equalization (VEQ) to boost voice above the ambient acoustic environment
  • Parametric equalizer for enhancing audio playback
  • HD voice listening experience over narrowband networks

Accessibility Features

To provide customization and personalization options for OEMs, the eS310 processor includes:

  • Personal Receiver Equalization -- to allow customers to select a receive frequency response that matches their hearing characteristic
  • Voice Stretch Mode – slows a calling party’s voice in real-time, retaining pitch accuracy, for improved comprehension during rapid conversations or for voice recording playback, including voicemail

Customization Features

To optimize performance, the eS305 processor includes:

  • A post-equalization (Post-EQ) filter for voice color tuning and to allow device manufacturers to manage frequency response
  • A receive multi-band compander (MBC) to improve audio quality and offer speaker distortion compensation

Easy Integration

Enabling easy design-in, the eS305 processor includes:

  • Audience’s AuViD 2.0 graphical software application to support the design and integration process, featuring step-by-step visual design tools to efficiently tune the audio features of the eS305 processor and customize voice capabilities
  • Auto microphone calibration to eliminate costly testing and per-unit adjustments on the production line
  • Graphical filter design tools for easy customization of Post-EQ and MBC filter design
  • All-digital interfaces designed to fit any tablet or handset style, in any design configuration

Efficient Platform

Designed for energy efficiency, the low-power, high performance chip is:

  • Packaged in a highly compact 3.5mm x 3.5mm, 32-pin BGA (0.5mm pitch).
  • Meets RoHS and Green requirements

Specifications

 Power Supplies
  • I/O: 3.3V~1.8V
Host Interface
  • Up to 1Mbps I2C interface
  • Up to 3Mbps UART
Digital Audio Interface
  • Four I2S/PCM interfaces
  • Supports digital microphone input


Click to download the Product Brief (PDF)

eS110

  • Print

earSmart™ eS110 Voice Processor

The earSmart™ eS110 voice processor from Audience brings the industry-leading smart-phone voice quality to feature phones. The eS110 is simple to integrate, fast to market and brings about maximum consumer impact. The eS110 voice processor is highly customizable, allowing device manufacturers to create differentiated products.

 

 

Product Highlights

Powerful Processing
  • Narrowband Non-Stationary and Stationary noise suppression in both transmit and receive paths
  • Handheld speakerphone (HHS) non-stationary and stationary noise suppression, in both transmit and receive paths
  • Acoustic echo cancellation (AEC)
  • Automatic receive voice equalization (VEQ) to boost voice above the ambient acoustic environment
  • Hi-Fi voice listening experience over Narrowband networks

Customization Features

To optimize performance, the eS110 Voice Processor includes:

  • A post-equalization (Post-EQ) filter for voice color tuning and to allow handset manufacturers to manage frequency response
  • A receive multi-band compander (MBC) to improve audio quality and offer speaker distortion compensation

Easy Integration

Enabling easy design-in, the eS110 Voice Processor includes:

  • Audience’s AuViD  graphical software application to support the design and integration process, featuring step-by-step visual design tools to efficiently tune the audio features of the eS110 Voice Processor and customize voice capabilities
  • Auto microphone calibration to eliminate costly testing and per-unit adjustments on the production line
  • All-digital interfaces designed to easily fit into current and future ID configurations

Efficient Platform

Designed for energy efficiency, the low-power, high performance chip is:

  • Packaged in a highly compact 3.5mm x 3.5mm, 36-pin BGA (0.5mm pitch).
  • Meets RoHS and Green requirements

Specifications

Power Supplies

  • I/O: 3.3V~1.8V
  • Core: 1.1V Typical

Host Interface

  • Up to 1Mbps I2C interface
  • Up to 3Mbps UART

Digital Audio Interface

  • Four I2S/PCM interfaces


Click to download the Product Brief (PDF)