Fraunhofer upHear Voice Quality Enhancement delivers a clear speech signal to the smart assistant, even under unfavorable acoustic conditions
LG has launched a localized version of its XBOOM AI ThinQ WK7 smart speaker with the Russian-speaking smart assistant “Alice” by Yandex. In order to provide Alice with user commands in the best possible audio quality, the WK7Y model is equipped with the Yandex.IO microphone array technology for far-field voice recording, which includes Fraunhofer’s upHear Voice Quality Enhancement (VQE). The Fraunhofer technology delivers a clean audio signal to the keyword spotter and speech recognizer, allowing Alice to hear voice commands accurately, no matter where in the room they are given — even while the smart speaker is playing music.
Fraunhofer upHear VQE processes the microphone array signals from the LG WK7Y. It removes interfering sounds for far-field operation and cancels out acoustic echoes caused by the speaker’s own loudspeaker signal during playback to enable barge-in. In this way, the voice assistant’s keyword spotter and speech recognizer are supplied with a clean speech signal via Yandex.IO.
About Fraunhofer upHear Voice Quality Enhancement
Fraunhofer upHear VQE processes microphone signals, thus enabling far-field full-duplex conversations in the full perceptible audio bandwidth for communication devices as well as far-field voice commands and barge-in during audio playback for smart assistant devices, always with outstanding audio quality. This is achieved by combining advanced multi‑channel acoustic echo cancellation, source localization, noise reduction and beamforming methods. The fully integrated technology is suitable for numerous applications, including natural language understanding in mobile and smart assistant devices, as well as conferencing solutions. upHear VQE’s flexibility allows for its application with a wide range of microphone array geometries built into mobile phones and smart assistant devices such as smart speakers, soundbars, cameras and TVs. It is optimized for mono and stereo as well as surround and even immersive audio devices.
Experience the upHear Voice Quality Enhancement technology at the CES Show in Las Vegas — visit Fraunhofer’s booth 20654 in South Hall 1 at the Las Vegas Convention Center.
Header image © Manuela Wamser – Fraunhofer IIS