Soniox Releases Groundbreaking AI for Speaker Recognition

Original Source Here

Soniox released a breakthrough in artificial intelligence for speaker diarization (separation) and identification. Soniox Speaker AI has achieved a 96% accuracy in detecting speakers for all kinds of business applications, making it 5x more accurate than solutions provided by Google, Microsoft and Amazon. This breakthrough unlocks a new dimension for voice and conversational applications.

Soniox, a company founded in April in 2020 in Redwood City, California, developed the world’s first self-learning artificial intelligence for automatic speech recognition. The company currently offers one of the leading cloud-based transcription engines available commercially – the one that audioXpress has been succesfuly using for interviews and general speech-to-text conversion. 

Knowing who said what is a fundamental element when building any kind of voice applications or conversational AI. Yet this seemingly basic and even obvious piece of information had eluded the greatest AI researchers for decades. Leading providers of speaker recognition such as Google, Amazon and Microsoft incur on average an error of 25%, meaning a quarter of speech is assigned to the wrong speaker, making recognized speaker information unusable for downstream application.

Attempting to develop conversational AI without knowing who asked a question or who gave an answer is infeasible and futile. Reliable speaker recognition is in fact a prerequisite for making conversational AI applications work.

Based on its core technology, Soniox now made a breakthrough in speaker recognition with artificial intelligence. Soniox Speaker Diarization AI has achieved a stunning accuracy of 96% for business applications, meaning 96% of speech is assigned to the correct speaker. With an error rate of just 4%, Soniox Speaker Diarization is 5 times more accurate than any other provider, smashing the status quo.

In addition to Speaker Diarization, Soniox released another breakthrough technology, Soniox Speaker Identification AI, which accurately identifies speakers based on voice profiles in all kinds of real-world situations.

Soniox Speaker AI not only transforms a single audio file into a multi-speaker transcription, but also serves real-time and low-latency applications, making Soniox the first in the world to support applications with such requirements.

“We have been truly living in the dark ages of conversational AI without reliable speaker information. With Soniox Speaker AI, you can now build voice and conversational AI applications you have always envisioned; applications that allow contact center managers to listen to the voice of their customers, or systems that enable recruiters to analyze interviewer and candidate performance, or medical documentation software that auto-identifies doctors’ prescriptions. With Soniox Speaker AI, the possibilities are endless,” the company states.


Trending AI/ML Article Identified & Digested via Granola by Ramsey Elbasheer; a Machine-Driven RSS Bot

%d bloggers like this: