The world's highest performance Audio Front Ends for voice-controlled products

 

 

Any voice-controlled product can work in a quiet room, but that's not where your customers live.

DSP Concepts’ TalkTo™ line of Audio Front Ends use Machine Learning and a suite of advanced microphone-processing algorithms to deliver dependable voice-control, even in the most hostile acoustic environments!

 


 

Anatomy of a Voice-Controlled Product

 

 

Audio Front End (AFE)

Conceptually, the AFE serves as a microphone cleaner. It uses raw microphone-data to detect, extract, and clean any voice-commands found in the ambient sound-field.  TalkTo front ends use a proprietary Machine Learning algorithm to actively strip away up to 30dB of interfering noise! 

Wake Word Engine (WWE)

Wake-Word Engines continuously scan the AFE-provided voice-stream, looking for the presence of a specific phrase (e.g. Alexa or OK-Hound).  The accuracy of the WWE is one of the primary drivers of UX-quality, and is highly dependent upon the purity of the AFE-generated voice-stream.

Back End Services

Once the wake-word is detected, the product forwards the extracted voice-command to a cloud-based or local voice-service. Here again, accuracy of the ASR (speech-to-text) and NLU (deciding intent) requires a high-quality voice-stream from the Audio Front End.

 

 


 

 

TalkTo Performance

 

The video below shows the 6-Microphone, Amazon Qualified, TalkTo - Set Top Box AFE running on an Amlogic A113 board.  The system is running stand-alone, directly below the TV's speakers (playout at 90+ dBC!).  Without the closed-loop benefit of AEC (there's no reference signal to eliminate), TalkTo's suite of advanced Machine Learning algorithms is still able to detect, characterize, and eliminate the interfering noise;  allowing the WWE and Voice Services to deliver a robust user-experience, even in the harshest of conditions!

 

 

 

 


 

 

TalkTo Variants

Voice controlled products span the spectrum of embedded design, from picowatt-sipping wearables to home-theater products with near limitless processing resources.  Accordingly, DSP Concepts has off-the shelf TalkTo designs for a wide variety of applications, each custom tailored to the capabilities and needs of the target environment.  For more information or to schedule a live demo, please contact info@dspconcepts.com
 

Smart Speaker

 

Set Top Box

Battery Optimized Devices

 

Wearable / Hearable 

 
 

Multi-channel Soundbar

Smart Home / IoT

 

 

TV / Smart Screen

 

 

For more information or to schedule a live demo, please contact info@dspconcepts.com!