TalkTo is a suite of machine learning and microphone processing algorithms that use adaptive learning technology to deliver a quiet-room experience in noisy and unpredictable environments. Now, says the company, hardware brands can easily build Alexa built-in devices that will perform well even in noisy situations – from a crowded dinner party to a boisterous kids play date – thanks to TalkTo’s industry-leading sound cancellation technology.

TalkTo is offered as a turnkey audio front end software solution that provides the following benefits:

  • Industry-leading sound cancellation – Adaptive Interference Canceller can cut through up to 30 decibels of unreferenced noise to activate Alexa in any environment
  • Unprecedented design flexibility – Supports two-mic, four-mic, six-mic and custom configurations with Acoustic Echo Cancellation (AEC) for up to seven channels
  • Highly scalable – Automatically optimizes for the needs and capabilities of the target application, including but not limited to smart home/IoT, televisions, soundbars, set top boxes, smart speakers, hearables and wearables
  • “Try before you buy” – Developers can access a free trial to evaluate the software and prototype new devices before purchasing a production license

Beyond the qualified configurations, product makers can tailor their mic configurations depending on how they want the device they’re building to function. TalkTo, says the company, is one of just four audio front end reference designs that currently meets Amazon’s rigorous standards.

“Companies who work in voice-enabled product design understand what this qualification by Amazon means – it is the gold-standard,” says Chin Beckmann, CEO of DSP Concepts. “Not only is TalkTo an incredibly flexible audio front end offered for Alexa Voice Service, our qualification by Amazon means that device manufacturers and audio dev teams can greatly accelerate their development cycles. We look forward to seeing how product makers will use it to accelerate the deployment of Alexa-enabled devices in a variety of end products.”

DSP Concepts

Related articles:
Audio/voice DSP tie-up eases high-end sound development
Is voice the next big thing?
Choosing a far-field voice recognition DSP
3D-printed ‘cocktail party listener’ picks out voices in a crowd
Audio processing engine is optimized for multi-core development

If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :    eeNews on Google News


Linked Articles