upHear Microphone Processing

Unleash the True Potential of any Microphone

When integrated into a device, upHear Microphone Processing guarantees an exceptional audio experience that will keep users connected and engaged. Designed to seamlessly adapt to varying acoustic conditions, however challenging they may be, our technology gives users the choice of what they want to hear and what they don’t.
upHear Microphone Processing offers a variety of technologies covering a broad range of use cases – from removing background noise to extracting a specific voice or capturing immersive audio.

(Multichannel) Echo Control

For easy barge-in and high-quality communication via smart speakers.

Beamforming

Improved intelligibility and SNR of far-field voice pickup.

Noise Reduction

Focus on the voice without being distracted by background sounds and noise.

Dereverberation

Improved intelligibility and comfort in reverberant rooms.

Automatic Gain Control

Capture the user's speech from any distance with constant loudness.

Spatial Upmix

Increases the spatial resolution of the recorded immersive sound.

Wind Noise Reduction

Perceiving optimum speech quality even in windy outdoor environments.

Audio Zoom

Realtime focus on specific sources or genera-tion of immersive spatial sound.

AI-based Noise Reduction

Advanced noise reduction capabilities meet low-complexity AI: upHear AI-Based Noise Reduction enables high-class performance while keeping a low complexity and energy footprint, which results in low battery consumption. Its compatibility with standard CPUs and DSPs omits any need for specialized costly GPUs or NPUs. The technology is deployable on edge devices or even in cloud services.
Despite its low demands on the hardware side, upHear AI-Based Noise Reduction delivers astonishing functionality: its adjustable intensity puts it into the hands of the user, how much of the background noise they want removed, giving them the ability to find the optimal balance between voice signals and ambience. The low processing delay enables interruption-free natural conversation. upHear AI-based Noise Reduction can be used at the sending as well as the receiving end. The technology is available as a standalone module and therefore can easily be used with any acoustic front end.

Typical Application Scenarios

VoIP Communication: Strong noise reduction with low processing delay independent of the device class

Content Creation: Capturing the best possible speech signals with a user-definable attenuation of background noises

Contact an upHear Expert for your Solution

Contact

Voice Quality Enhancement

The technology brings microphone processing for smart assistants and VoIP applications to a whole new level. It enables voice-controlled interactions with phones, speakers, and soundbars as well as clear voice for optimal intelligibility. This integrated solution improves voice recognition by removing interference and echoes, ensuring clear communication.
Through the combination of advanced echo control, beamforming, and noise reduction algorithms, outstanding voice quality is achieved in any environment. It works seamlessly with all kinds of devices and conferencing solutions, delivering a superior user experience.
upHear Voice Quality Enhancement is a flexible solution that can be applied and adapted to several hardware constellations, such as various microphone and loudspeaker setups, while satisfying the computational complexity requirements.

Typical Application Scenarios

VoIP Communication: Crystal-clear speech on all kinds of devices by removing background noise, acoustical echoes, and other interfering sources with low processing delay.

Speech Assistants: Improved signals let the voice assistant understand the user’s commands even in challenging environments

Contact an upHear Expert for your Solution

Contact

Spatial Audio Microphone Processing

The technology enhances sound capture for 360° cameras and mobile devices. It delivers natural, immersive audio by localizing sound sources with high precision while recording ambient sounds. Even compact devices are empowered to capture artifact-free immersive audio, increase speech intelligibility and extract desired sounds.
upHear Spatial Audio Microphone Processing transforms the captured sound into popular surround and immersive audio formats in real time. Features include noise reduction, beamforming, dereverberation, sound equalization, wind noise reduction, gain control, and audio zoom. The solution is highly customizable, catering for the specific tastes of the audience or user.

Typical Application Scenarios

General Recordings: Spatial sound capture facilitates the recreation of the original audio experience at the recording location

Concert Experience: Accurate immersive capture of live performances without annoying wind noise

Content Creation: Optimal speech capture without background sounds and interfering sources

Audio Zoom: Enhanced perception of sound sources depending on the user‘s preference

Contact an upHear Expert for your Solution

Contact