Transform the possibilities of real-world voice control and cut through all the noise to deliver better ASR and local command results. Easily integrate Alexa Voice Service and Google Voice Assistant and extend their range to an industry-leading 6 meters. TalkTo includes an Adaptive Interference Canceller to eliminate interfering noise sources even without a reference signal, and supports multichannel AEC, and custom mic array geometries.
Eliminate interfering noise sources, even without a reference signal with Adaptive Interference Canceller (AIC).
Easily integrate Alexa Voice Service (AVS) into products where external noise is problematic.
Push what’s possible with industry’s most advanced multichannel system and beamforming for up to 8 microphones.
TalkTo is an audio front-end (AFE) that combines advanced signal processing techniques to create clean audio signals for voice assistants and ASR engines. TalkTo provides excellent voice performance and supports from 2 to 8 microphones in a variety of configurations. TalkTo has passed AVS v. 2.1 premium audio qualification using as few as 4 microphones.
TalkTo is highly configurable, scalable, and hardware agnostic, whether the target processor is a small low power MCU, a DSP or a powerful multicore SOC. Many recommended microphone topologies are available and customizable for unique form factors and industrial designs.
Adaptive Interference Cancellation (AIC) reduces external noises by 30dB allowing voice products to coexist with other machines or entertainment devices that generate interfering noise. With AIC, exclusive to DSP Concepts, a soundbar positioned in front of a loud TV can still hear users say commands without raising their voices.
Acoustic Echo Cancellation (AEC) reduces reverb on the received speech and improves far-field voice detection for devices generating output levels of 100dB SPL at 1 meter. DSP Concepts provides the leading multichannel AEC solution for the most demanding product requirements.
Beamformers are spatial filters that apply gain based on the direction of sound while steering the beam at the user to maximize the signal to noise ratio (SNR) available for signal processing. This reduces the impact of a reverberant room.
Direction of Arrival (DoA) determines the direction of the desired voice signal to steer the adaptive beamformer. Improves performance in diffused noise condition by directing the pickup beam toward the desired speech. Example: Babble noise
Quiescent Sound Detection turns off the input signal processing when there is no input signal of interest to provide low power voice wakeup.
Provide users the choice and flexibility to interact with multiple voice assistant services thanks to TalkTo’s wake-word flexibility combined with an audio front end that can be configured for multiple cloud assistants or local command processing.
TalkTo is available in multiple variants, each scaled and optimized for the needs and capabilities of the target application, from a small low power MCU, a DSP or a powerful multicore SOC.
|
|
|
|
|
|
|
|
---|---|---|---|---|---|---|---|
Smart Home & IoT | Appliances | Hearables & Wearables | Medical & Fitness | Conference Speaker | Home Audio | Automotive | |
1 mic | 1-2 mic | 1-2 mic | 2/4/6 mic | 2/4/6 mic | 2-4 mic | >4 mic | |
Beamformers | |||||||
AEC | |||||||
AIC | |||||||
High dB SPL barge-in | |||||||
MCU | |||||||
DSP | |||||||
SoC |