# In-Ear-Voice: Towards Milli-Watt Audio Enhancement With Bone-Conduction Microphones for In-Ear Sensing Platforms

arXiv: https://arxiv.org/abs/2309.02393 · HTML: https://mlsanity.com/paper/2309.02393/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 45 references that are in the map.
- First posted on arXiv 5 Sep 2023.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Fixed Point Quantization of Deep Convolutional Networks](https://mlsanity.com/paper/1511.06393/) (2015)
- [CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs](https://mlsanity.com/paper/1801.06601/) (2018)
- [Speaker Diarization with LSTM](https://mlsanity.com/paper/1710.10468/) (2017)
- [ICASSP 2022 Deep Noise Suppression Challenge](https://mlsanity.com/paper/2202.13288/) (2022)
- [A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancement](https://mlsanity.com/paper/1709.08243/) (2017)
- [Personal VAD: Speaker-Conditioned Voice Activity Detection](https://mlsanity.com/paper/1908.04284/) (2019)
- [A Perceptually-Motivated Approach for Low-Complexity, Real-Time Enhancement of Fullband Speech](https://mlsanity.com/paper/2008.04259/) (2020)
- [Personal VAD 2.0: Optimizing Personal Voice Activity Detection for On-Device Speech Recognition](https://mlsanity.com/paper/2204.03793/) (2022)
- [Spiking neural networks trained with backpropagation for low power neuromorphic implementation of voice activity detection](https://mlsanity.com/paper/1910.09993/) (2019)
- [On training targets for noise-robust voice activity detection](https://mlsanity.com/paper/2102.07445/) (2021)
- [Enrollment-less training for personalized voice activity detection](https://mlsanity.com/paper/2106.12132/) (2021)
- [A Bin Encoding Training of a Spiking Neural Network-based Voice Activity Detection](https://mlsanity.com/paper/1910.12459/) (2019)

## Built on by (most cited first, 3 of 3)

- [Ultra-Efficient On-Device Object Detection on AI-Integrated Smart Glasses with TinyissimoYOLO](https://mlsanity.com/paper/2311.01057/) (2023)
- [Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors](https://mlsanity.com/paper/2407.11828/) (2024)
- [Performance Analysis of Edge and In-Sensor AI Processors: A Comparative Review](https://mlsanity.com/paper/2603.08725/) (2026)

## Abstract (arXiv)

The recent ubiquitous adoption of remote conferencing has been accompanied by omnipresent frustration with distorted or otherwise unclear voice communication. Audio enhancement can compensate for low-quality input signals from, for example, small true wireless earbuds, by applying noise suppression techniques. Such processing relies on voice activity detection (VAD) with low latency and the added capability of discriminating the wearer's voice from others - a task of significant computational complexity. The tight energy budget of devices as small as modern earphones, however, requires any system attempting to tackle this problem to do so with minimal power and processing overhead, while not relying on speaker-specific voice samples and training due to usability concerns. This paper presents the design and implementation of a custom research platform for low-power wireless earbuds based on novel, commercial, MEMS bone-conduction microphones. Such microphones can record the wearer's speech with much greater isolation, enabling personalized voice activity detection and further audio enhancement applications. Furthermore, the paper accurately evaluates a proposed low-power personalized speech detection algorithm based on bone conduction data and a recurrent neural network running on the implemented research platform. This algorithm is compared to an approach based on traditional microphone input. The performance of the bone conduction system, achieving detection of speech within 12.8ms at an accuracy of 95% is evaluated. Different SoC choices are contrasted, with the final implementation based on the cutting-edge Ambiq Apollo 4 Blue SoC achieving 2.64mW average power consumption at 14uJ per inference, reaching 43h of battery life on a miniature 32mAh li-ion cell and without duty cycling.