Outstanding results
Veridas will host two sessions next December 14-16 at the NIST Speaker Recognition Evaluation 2021 workshop after obtaining excellent results at the 2021 Speaker Recognition Evaluation (SRE21).
This evaluation is the next in an ongoing series of speaker recognition evaluations conducted by the NIST since 1996. The objectives of the evaluation series are to effectively measure the system-calibrated performance of the current state of technology, provide a common framework that enables the research community to explore promising new ideas in speaker recognition, and support the community in their development of advanced technology incorporating these ideas.
In addition, Veridas is also currently participating in the ongoing 2020 CTS Challenge. The primary task is determining whether a specified target speaker is speaking during a given speech segment with data sources containing multilingual speech. Veridas’ engine, thanks to its text and language-independent features, is performing at the top of the board (check here).
Veridas has performed at the top of the list in both evaluations. After these results, NIST evaluators have invited Veridas subject-matter experts to host two sessions at the next NIST SRE21 workshop to explain the performance of the das-Peak voice biometric engine in further detail.
Top technology and transparency, our core values
Veridas has been submitting its technologies to NIST’s evaluations since 2018 and continues to do so with the firm belief that constant scrutiny is the only way to maintain its position as a global leader in the biometric solutions market.
The biometric engines submitted to NIST evaluations are the same that we offer to clients in our cloud. The evaluation results become even more significant as they are tested on the actual commercial product rather than on specific variations adjusted to perform better under each category’s requirements. Veridas das-Peak engine is balanced and a top-performer in every scenario, making it a secure and feasible solution for real-life use cases.
