Preech: A System for Privacy-Preserving Speech Transcription

Abstract

New Advances in machine learning have made Automated Speech Recognition (ASR) systems practical and more scalable. These systems, however, pose serious privacy threats as speech is a rich source of sensitive acoustic and textual information. Although offline and open-source ASR eliminates the privacy risks, its transcription performance is inferior to that of cloud-based ASR systems, especially for real-world use cases. In this paper, we propose Pr$\epsilon \epsilon$ch, an end-to-end speech transcription system which lies at an intermediate point in the privacy-utility spectrum. It protects the acoustic features of the speakers' voices and protects the privacy of the textual content at an improved performance relative to offline ASR. Additionally, Pr$\epsilon \epsilon$ch provides several control knobs to allow customizable utility-usability-privacy trade-off. It relies on cloud-based services to transcribe a speech file after applying a series of privacy-preserving operations on the user's side. We perform a comprehensive evaluation of Pr$\epsilon \epsilon$ch, using diverse real-world datasets, that demonstrates its effectiveness. Pr$\epsilon \epsilon$ch provides transcriptions at a 2% to 32.25% (mean 17.34%) relative improvement in word error rate over Deep Speech, while fully obfuscating the speakers' voice biometrics and allowing only a differentially private view of the textual content.

arXiv comment21 pages, 8 figures, 5 tables. The paper is accepted at the 29th USENIX Security Symposium - URL: https://www.usenix.org/conference/usenixsecurity20/presentation/ahmed-shimaa

References in corpus (11)

• WaveNet: A Generative Model for Raw Audio
• SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Tacotron: Towards End-to-End Speech Synthesis
• The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods
• The GDPR & Speech Data: Reflections of Legal and Technology Communities, First Steps towards a Common Understanding
• Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?
• VoiceMask: Anonymize and Sanitize Voice Input on Mobile Devices
• Attacking Speaker Recognition With Deep Generative Models
• Emotionless: Privacy-Preserving Speech Analysis for Voice Assistants
• Shrinkwrap: Differentially-Private Query Processing in Private Data Federations

Cited by in corpus (1)

• Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks