... bringing super-human hearing to very human spaces

Any voice-controlled product can work well in a quiet room, but that's not where your customers live.  TalkTo™ uses a suite of proprietary Machine Learning & Microphone Processing algorithms to bring quiet-room performance to the noisy & unpredictable spaces of everyday life.





Anatomy of a Voice-Controlled Product



Audio Front End (AFE)

Conceptually, the AFE serves as a microphone cleaner. It uses the raw, noisy audio from the microphones to detect, extract, and clean any speech-activity found in the ambient sound field.  A cleaned, reconstructed voice-stream is output to the Wake Word Engine.

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").  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 extracted voice-command is passed to a [cloud-based or local] voice-service which converts speech-to-text (ASR) and determines user-intent (NLU). Again, accuracy relies on a high-quality voice-stream from the Audio Front End.

Speaker Processing

For a high-quality voice-experience, products with audio-output(s) must have low speaker-distortion. To achieve this, the output-audio is processed to ensure it doesn't exceed the physical capabilities of the speaker(s). Audio Weaver® is a fast path solution to this problem.





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!).  Even without the closed-loop benefit of AEC (there's no reference signal to eliminate), the TalkTo AFE is still able to detect and extract faint voice-commands from the ambient sound-field;  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!