Happy New Year! As we reflect back on 2017, and prepare to head into 2018, it is difficult to deny that the speech analytics industry is heating up. Many software vendors like VBG are benefitting from the public’s increasing willingness to use speech as a computing interface. We can all thank Apple for Siri, Amazon for Alexa, and Google for Google Home, among others. 2018, 2019, and beyond should show strong growth for many companies working with speech technologies.
One of the primary reasons that people are using these technologies at an increasing pace, is that they finally are working well after years of near misses. At the heart of these innovations is “deep learning”, a collection of algorithms under the AI umbrella that are offering significant accuracy improvements and convenience for users and systems administrators alike.
VBG uses deep learning techniques in a variety of ways, and we'll share some of our product details in future articles. For now, we thought we would share some of our software development plans for 2018.
Speech Enhancement (SE). This April, we plan to speak at SpeechTek in Washington D.C. The topic we have chosen is “speech enhancement” or SE. VBG is using deep learning to handle noise in a way that’s quite different from traditional filters. This capability is being released into our production software platform soon. And, we’ll write with more details about SE following our presentation.
Security Enhancements. The EU's General Data Protection Regulation (GDPR) goes into effect at the end of May. As VBG has a global customer base, we are putting the finishing touches on numerous system changes which will help us to offer greater protection of personal data and support the ability of our clients and partners to provide its end users with control over their data. More will be written about GDPR in the coming months as well.
Scaling Improvements. As VBG has grown, we’ve needed to make changes to our data storage model to support larger and larger customers. We’ll be rolling out a new database stack this year which should allow to support user communities in the 20-50MM+ range, all with the same speed and stability our customers have come to know and expect from us.
VMM-4 Engine Coming. And finally, our next generation voice biometric engine, the VMM-4, is currently under development. It will feature the very latest in deep learning techniques, and will likely offer optional support for several new functions, such as emotion detection. We don’t have a definite release date yet, but we are aiming for a 2018 release.
Check back again for updates to these items and others. And, best wishes for a happy and prosperous 2018!
Peter is an avid reader, particularly of high-tech topics. These articles express his opinion only, but he hopes you enjoy them!
Other Related Articles You May Enjoy
Click on any article title to read ...