If you’re attending AES New York 2017 on October 18 through 21, we invite you to hear DSP Concepts’ Chief Technology Officer and founder, Dr. Paul Beckmann explain and demonstrate some of the latest developments in voice recognition and audio digital signal processing.
Don’t miss these compelling sessions and the opportunity to meet with Paul. Here’s a quick overview of what he will be discussing.
AES 143rd Convention 2017 New York
Friday, October 20, 10:45 a.m. – 12:15 p.m. Room PD07, Javitz Center
Session topic: Agile Audio Product Development – Paul Beckmann
During his talk, Paul will focus on recent advances in design tools for audio product developers that streamline the development and tuning of real-time audio processing software. Sophisticated audio features are now within reach of most companies, including those without a dedicated design team.
Friday, October 20, 3:15 p.m. – 4:45 p.m. Room PD09, Javitz Center
Session topic: Front End Processing for Voice Enabled Products – Paul Beckmann
Voice UI has become an important feature in consumer and automotive audio products. Many OEMS are scrambling to incorporate there features and have little or no experience with microphone processing. In this session, Paul will discuss the front end audio processing required by a device to properly interface to a cloud based ASR engine. He’ll discuss beamforming, echo cancellation, direction of arrival estimation, and noise reduction. Paul will also demonstrate how the algorithms must be designed to work in concert for far field voice pickup and the difficult to achieve "barge in" feature. He’ll also present a novel metric which is correlated with performance and allows easy comparison of beamformer designs.