ZenVoice Bone algorithm delivers superior voice clarity in noisy environments with Bosch Sensortec’s advanced BMA550 bone conduction sensor

Aizip and Bosch Sensortec jointly win 2024 Best of Sensors Award at Sensors Converge for noise reduction solution in hearable device technology

Multiple people watching their mobile phones, a smiling woman in the focus watching her mobile phone

Aizip's ZenVoice Bone algorithm coupled with Bosch Sensortec's BMA550 bone conduction sensor, delivers advanced noise reduction in TWS earbuds.
Leveraging the BMA550 sensor's capabilities, ZenVoice Bone excels in noise reduction, interference separation, and voice capture, while operating efficiently on low-power devices.
The collaboration won the 2024 Best of Sensors Award in the Medical & Wearables section at the Sensors Converge Conference and Expo.

In a significant advancement for the hearable technology sector, Aizip has collaborated with Bosch Sensortec to develop the ZenVoice Bone, a cutting-edge deep noise reduction algorithm designed to enhance voice clarity in true wireless stereo (TWS) earbuds, even in extremely noisy environments. This collaboration leverages Bosch Sensortec's innovative BMA550 bone conduction sensor and Aizip's advanced neural network architecture to deliver unparalleled speech intelligibility.

The BMA550 sensor, with its high-bandwidth accelerometer, is integral to the ZenVoice Bone solution, facilitating the detection of bone-conducted voices and enabling effective ambient noise filtering through smart 'voice enhancement'. Offering 5-7 times lower noise than standard accelerometers, the BMA550 ensures clear body sound crucial for noise suppression and speech enhancement. Its low power consumption and wide signal bandwidth of up to 2350Hz make it the ideal choice for always-on speech/voice applications.

Aizip's Zenet neural network architecture complements the BMA550 by providing highly efficient audio processing capabilities. ZenVoice Bone models achieve a remarkable 10-fold reduction in both processing power and memory requirements without compromising noise-handling efficiency. This integration allows the deployment of sophisticated audio intelligence on compact IC chips, significantly reducing costs and power consumption.

Key features and advantages

Superior noise reduction: ZenVoice Bone maintains underlying speech while removing most noise, even in signal-to-noise ratios as low as -15 dB.
Interference separation: The solution can distinguish an end user's voice from background speech without requiring voice registration, a feat impossible with single microphone solutions.
Compact and efficient: ZenVoice Bone operates efficiently on resource-restricted hardware, with models ranging from 60 KB to 300 KB in memory footprint, supporting real-time noise elimination with minimal latency.
Voice capture: The BMA550's low noise and wide bandwidth capture a broad spectrum of voice information, essential for the ZenVoice Bone's ability to restore speech amidst loud background noises, such as wind at 85db.
Low power consumption: The solution's modest computational demand makes it suitable for low-power, compact devices like TWS earbuds and hearing aids.

Real-world applications and impact

ZenVoice Bone's ability to deliver clear communication in noisy settings positions it as a transformative technology for various hearable devices, including TWS earbuds, hearing aids, and headsets. The integration of Bosch Sensortec's BMA550 sensor and Aizip's software not only enhances user experience but also broadens the potential applications of hearable devices by extending battery life and reducing cost.

For example, the spectrogram below demonstrates the ZenVoice Bone's effectiveness in a high-noise environment, where it isolates and reconstructs an end user’s voice amidst 85db wind noise.

A spectogram — Spectrograms demonstrating ZenVoice Bone algorithm’s effectiveness on reducing high noise: From top to bottom 1. Microphone input containing user’s voice + ~85db wind noise; 2. Signal acquired from Bosch Sensortec’s BMA550 bone conduction sensor under the same condition. Note that the low frequency part is cleaner than the microphone input while high frequency is missing; 3. Output of the ZenVoice Bone algorithm, denoised version of the end user voice.

This collaboration underscores the symbiotic relationship between hardware and software in advancing noise reduction technology. The BMA550 sensor's superior capabilities are instrumental in enabling the ZenVoice Bone algorithm to function effectively, providing the necessary data fidelity to perform its sophisticated noise suppression and speech enhancement tasks.

“The BMA550 sensor data, featuring ultra-low noise and very wide bandwidth for bone conduction, significantly enhances the ZenVoice Bone algorithm's ability to recover important voice information from background noise, ensuring clear voice output,”
says Yuan Lu, Co-founder and President at Aizip.

Conversely, the advanced neural network architecture developed by Aizip brings out the full potential of the BMA550 sensor, showcasing how integrated solutions can drive technological progress. This collaboration highlights the importance of integrating cutting-edge sensor technology with advanced AI solutions to meet evolving consumer demands and set new standards in the audio technology industry.

"Collaborations with experts like Aizip, who specialize in neural networks for hearable applications, enable Bosch Sensortec to deliver sophisticated solutions. By integrating our partners' domain expertise with our advanced sensor technology, we create innovative offerings for our customers,"
says Marcellino Gemelli, Head of Global Business Development at Bosch Sensortec.

Aizip and Bosch Sensortec jointly applied for the 2024 Best of Sensors Award at the Sensors Converge Conference and Expo, held from June 24 to 26, 2024. They were nominated as finalists and won the Award in the Medical & Wearables section, recognizing their collaborative efforts to revolutionize noise reduction in TWS earbuds with the BMA550 bone conduction sensor. This accolade underscores the innovative impact and industry significance of this collaboration.