Prεεch: A System for Privacy-Preserving Speech Transcription

09/09/2019
by   Shimaa Ahmed, et al.
0

New Advances in machine learning and the abundance of speech datasets have made Automated Speech Recognition (ASR) systems, with very high accuracy, a reality. ASR systems offer their users the means to transcribe speech data at scale. Unfortunately, these systems pose serious privacy threats as speech is a rich source of sensitive acoustic and textual information. Although offline ASR eliminates the privacy risks, we find that its transcription performance is inferior to that of cloud-based ASR systems, especially for real-world recordings. In this paper, we propose Prϵϵch, an end-to-end speech transcription system which lies at an intermediate point in the privacy-utility spectrum of speech transcription. 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. Prϵϵch 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 Prϵϵch, using diverse real-world datasets, that demonstrates its effectiveness. Prϵϵch provides transcriptions at a 12.30 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.

READ FULL TEXT
research
09/09/2019

Spreech: A System for Privacy-Preserving Speech Transcription

New Advances in machine learning and the abundance of speech datasets ha...
research
04/01/2021

Configurable Privacy-Preserving Automatic Speech Recognition

Voice assistive technologies have given rise to far-reaching privacy and...
research
07/25/2023

On-Device Speaker Anonymization of Acoustic Embeddings for ASR based onFlexible Location Gradient Reversal Layer

Smart devices serviced by large-scale AI models necessitates user data t...
research
03/26/2022

Towards Privacy-Preserving Speech Representation for Client-Side Data Sharing

Privacy and security are major concerns when sharing and collecting spee...
research
08/13/2020

Textual Echo Cancellation

In this paper, we propose Textual Echo Cancellation (TEC) - a framework ...
research
10/11/2022

An Experimental Study on Private Aggregation of Teacher Ensemble Learning for End-to-End Speech Recognition

Differential privacy (DP) is one data protection avenue to safeguard use...
research
02/16/2022

Privacy-preserving Similarity Calculation of Speaker Features Using Fully Homomorphic Encryption

Recent advances in machine learning techniques are enabling Automated Sp...

Please sign up or login with your details

Forgot password? Click here to reset