# Paralinguistic Privacy Protection at the Edge

arXiv: https://arxiv.org/abs/2011.02930 · HTML: https://mlsanity.com/paper/2011.02930/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2020.

## Built on by (most cited first, 5 of 5)

- [Configurable Privacy-Preserving Automatic Speech Recognition](https://mlsanity.com/paper/2104.00766/) (2021)
- [Privacy against Real-Time Speech Emotion Detection via Acoustic Adversarial Evasion of Machine Learning](https://mlsanity.com/paper/2211.09273/) (2022)
- [Safeguarding Privacy in Edge Speech Understanding with Tiny Foundation Models](https://mlsanity.com/paper/2502.01649/) (2025)
- [Privacy-Preserving End-to-End Spoken Language Understanding](https://mlsanity.com/paper/2403.15510/) (2024)
- [Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding](https://mlsanity.com/paper/2609.28344/) (2026)

## Abstract (arXiv)

Voice user interfaces and digital assistants are rapidly entering our lives and becoming singular touch points spanning our devices. These always-on services capture and transmit our audio data to powerful cloud services for further processing and subsequent actions. Our voices and raw audio signals collected through these devices contain a host of sensitive paralinguistic information that is transmitted to service providers regardless of deliberate or false triggers. As our emotional patterns and sensitive attributes like our identity, gender, well-being, are easily inferred using deep acoustic models, we encounter a new generation of privacy risks by using these services. One approach to mitigate the risk of paralinguistic-based privacy breaches is to exploit a combination of cloud-based processing with privacy-preserving, on-device paralinguistic information learning and filtering before transmitting voice data. In this paper we introduce EDGY, a configurable, lightweight, disentangled representation learning framework that transforms and filters high-dimensional voice data to identify and contain sensitive attributes at the edge prior to offloading to the cloud. We evaluate EDGY's on-device performance and explore optimization techniques, including model quantization and knowledge distillation, to enable private, accurate and efficient representation learning on resource-constrained devices. Our results show that EDGY runs in tens of milliseconds with 0.2% relative improvement in "zero-shot" ABX score or minimal performance penalties of approximately 5.95% word error rate (WER) in learning linguistic representations from raw voice signals, using a CPU and a single-core ARM processor without specialized hardware.