• Skip to main content
  • Skip to secondary menu
  • Skip to primary sidebar
  • Skip to footer
  • Our Services
  • Contact Us
  • Newsletter
  • Top Nav Social Icons

Mobile ID World

Mobile ID World

Identification Revolution

  • Mobile ID
    • What Is Mobile ID?
    • Identity Associations
    • Premier Partners
    • FAQ
  • News
  • Solutions
    • Behavioral
    • Facial Recognition
    • Fingerprint Biometrics
    • Iris Biometrics
    • Second Factor
    • Smart Cards
    • Smartphones
    • Vital
    • Voice
    • Wearable Tech
    • Other
  • Applications
    • Access Control
    • Cloud Technology
    • Commerce
    • Enterprise
    • Healthcare
    • Identification
    • Internet of Things
    • Law Enforcement
    • Strong Online Authentication
  • Exclusive
    • Interviews
    • Featured Articles
    • Podcasts
  • Companies
  • Events

AI Startup Releases Tool for Detecting Speech Recognition Bias

July 20, 2020

“Artie is hoping that developers will be able to use the platform to identify and eventually eliminate bias in speech recognition systems, which will in turn prevent discrimination based on age, gender, accent, and other factors.”

AI Startup Releases Tool for Detecting Speech Recognition Bias

An AI startup has released a new tool to measure bias in speech recognition systems. The Artie Bias Corpus (ABC) was put together using Mozilla’s Common Voice corpus, and includes 1,712 individual audio clips and transcriptions.

Those clips represent 2.4 hours of total audio, and include recordings of people speaking in 17 distinct English accents. Those people are divided into eight unique age ranges between 18 and 80, each with three gender categories. All of the demographic information is self-reported, and was provided with the consent of the speaker.

Artie is hoping that developers will be able to use the platform to identify and eventually eliminate bias in speech recognition systems, which will in turn prevent discrimination based on age, gender, accent, and other factors. For example, a recent study found that leading speech recognition systems (from companies like Apple, Amazon, and Google) were collectively far less accurate when applied to black voices (a 35 percent error rate) than white ones (19 percent).

Artie itself is currently developing a platform for mobile games that leverage AI in some capacity. However, the ABC tool can ultimately be used to assess any speech recognition system, regardless of industry.

“Bias can render a technology unusable for someone because of their demographic,” said Artie lead scientist and Mozilla research fellow Josh Meyer. “Even for well-resourced languages like English, state of the art speech recognizers cannot understand all native accents reliably, and they often understand men better than women. The solution is to face the problem, and work toward solutions.”

To test its tool, Artie used ABC to analyze Mozilla’s open source DeepSpeech models, finding that it favored U.S. and British accents. Artie also found that a publicly available Google model had more gender bias than a publicly available counterpart from Amazon.

The results show that bias is still a problem for many voice recognition providers, even if that bias is not as well publicized as the racial bias that has been found in many facial recognition systems.

Source: Venture Beat

–

(Originally posted on FindBiometrics)

Filed Under: Industry News Tagged With: AI, AI bias, Artie Bias Corpus, Artificial Intelligence, bias, machine learning, racial bias, speech recognition, voice interaction, voice interface technology

Related News & Articles

Sensory Launches Free VoiceHub Development Platform

Xiaomi Patents Full-Screen In-Display Fingerprint Recognition System

ZenGo Updates Its Biometrically Secured Crypto Wallet

Primary Sidebar

Learn About Mobile ID and Aviation

Tweets

Sponsored Links

facetec logo

FaceTec’s patented, industry-leading 3D Face Authentication software anchors digital identity, creating a chain of trust from user onboarding to ongoing authentication on all modern smart devices and webcams. FaceTec’s 3D FaceMaps™ make trusted, remote identity verification finally possible. As the only technology backed by a persistent spoof bounty program and NIST/iBeta Certified Liveness Detection, FaceTec is the global standard for Liveness and 3D Face Matching with millions of users on six continents in financial services, border security, transportation, blockchain, e-voting, social networks, online dating and more. www.facetec.com

FACEPHI is a global leader in Facial Recognition technology and in Mobile Biometrics technologies. With a strong concentration in the financial sector, FacePhi’s product is rapidly becoming a service used by banks all over the world. Its implementation doesn’t just save money, it is also a way to attract clients and build loyalty, while increasing the security of transactions for both the customer and the business. To learn more about FacePhi, visit https://www.facephi.com/en/

Recent Posts

  • NordPass, Yahoo! Japan, and Regula Keep Up Mobile Biometrics Momentum
  • NordPass Enables Biometric, TOTP-secured 2FA for Business Users
  • Mastercard Solution Certified Under UK’s Digital ID Framework
  • Transatlantic Digital Traveler Identity Project Gets High-Profile Tech Partner
  • Digital Identity Tech Demo Online Event

Footer

  • About Us
  • Company Directory
  • Advertise With Us
  • Contact Us
  • Privacy Policy
  • Terms of Use
  • Archives
  • CCPA: Do not sell my personal info.

Follow Us

Copyright © 2023 MobileIDWorld