Understanding the Tradeoffs in Client-Side Privacy for Speech Recognition

by   Peter Wu, et al.

Existing approaches to ensuring privacy of user speech data primarily focus on server-side approaches. While improving server-side privacy reduces certain security concerns, users still do not retain control over whether privacy is ensured on the client-side. In this paper, we define, evaluate, and explore techniques for client-side privacy in speech recognition, where the goal is to preserve privacy on raw speech data before leaving the client's device. We first formalize several tradeoffs in ensuring client-side privacy between performance, compute requirements, and privacy. Using our tradeoff analysis, we perform a large-scale empirical study on existing approaches and find that they fall short on at least one metric. Our results call for more research in this crucial area as a step towards safer real-world deployment of speech recognition systems at scale across mobile devices.



There are no comments yet.


page 1

page 2

page 3

page 4


An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models

Speaker-independent speech recognition systems trained with data from ma...

Increasing Adversarial Uncertainty to Scale Private Similarity Testing

Social media and other platforms rely on automated detection of abusive ...

VoiceMask: Anonymize and Sanitize Voice Input on Mobile Devices

Voice input has been tremendously improving the user experience of mobil...

Cloud-based MPC with Encrypted Data

This paper explores the privacy of cloud outsourced Model Predictive Con...

Private Language Model Adaptation for Speech Recognition

Speech model adaptation is crucial to handle the discrepancy between ser...

VJAĠĠ– A Thick-Client Smart-Phone Journey Detection Algorithm

In this paper we describe Vjaġġ, a battery-aware journey detection algor...

Personalization of End-to-end Speech Recognition On Mobile Devices For Named Entities

We study the effectiveness of several techniques to personalize end-to-e...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.