FB pixel

Speechmatics says dramatic speech recognition bias reduced with unlabelled training data

Speechmatics says dramatic speech recognition bias reduced with unlabelled training data

Speechmatics has developed a speech recognition model that it says improves accuracy in understanding groups that have typically been challenging for natural language processing (NLP) systems, such as African Americans and children.

The new Autonomous Speech Recognition software applies the latest deep learning techniques and introduces Speechmatics’ breakthrough self-supervised models, according to the company announcement.

The company refers to Stanford’s ‘Racial Disparities in Speech Recognition’ study, which showed overall accuracy rates below 70 percent for African Americans using both Google and Amazon models, and says its new software delivers overall accuracy of 82.8 percent for African American voices. This difference equates to a 45 percent error reduction, Speechmatics says, or roughly three words per sentence on average.

The lack of manually tagger or labeled data from the above groups for algorithm training has resulted in a lack of accuracy in speech recognition being commonplace, according to Speechmatics. The company says it has avoided the issue entirely by training its algorithms on huge volumes of unlabelled data from the internet, such as podcasts and social media content. Speechmatics collected 1.1 million hours of audio to replace a dataset of 30,000 hours.

Speechmatics says, based on the open-sourced Common Voice project, that its technology was 91.8 percent accurate at understanding children’s voices, compared to 83.4 percent for Google and 82.3 percent for DeepGram.

“We are on a mission to deliver the next generation of machine learning capabilities and through that offer more inclusive and accessible speech technology,” comments Speechmatics CEO Katy Wigdahl. “This announcement today is a huge step towards achieving that mission.

“Our focus on tackling AI bias has led to this monumental leap forward in the speech recognition industry and the ripple effect will lead to changes in a multitude of different scenarios. Think of the incorrect captions we see on social media, court hearings where words are mistranscribed and eLearning platforms that have struggled with children’s voices throughout the pandemic. Errors people have had to accept until now can have a tangible impact on their daily lives.”

A report from Speechmatics at the beginning of 2021 highlighted the importance of voice biometrics for getting the most value out of speech apps.

Article Topics

 |   |   |   |   |   |   |   |   | 

Latest Biometrics News


Kenya raises issuance targets for digital IDs and passports

Everything being equal, Kenya plans to issue at least three million digital national IDs and one million biometric passports before…


IOM and Japan back biometrics at Sri Lanka ports of entry

Biometric technology use continues to grow at airports around the world. Air transport industry IT provider SITA predicts that by…


Kuwait fingerprints 2M as biometric data registration deadline nears

Kuwait is finalizing its program of collecting fingerprints for the country’s central biometric database as the June deadline for completion….


Xperix OCR software deployed for Brazil border control in deal with Akiyama Group

South Korea-based biometrics provider Xperix Inc. has announced the successful integration of its RealPass-N Optical Character Recognition (OCR) algorithm and…


The UK’s election may spell out the future of its national ID cards

Identity cards are back among the UK’s top controversial topics – thanks to the upcoming elections and its focus on…


Challenges in face biometrics addressed with new tech and research amid high stakes

Big biometrics contracts and deals were the theme of several of the stories on that drew the most interest from…


Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Most Read From This Week

Featured Company

Biometrics Insight, Opinion

Digital ID In-Depth

Biometrics White Papers

Biometrics Events