Spreech: A System for Privacy-Preserving Speech Transcription

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 Prch, 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. Prch 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 Prch, using diverse real-world datasets, that demonstrates its effectiveness. Prch provides transcriptions at a 12.30% to 32.24% 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.
View on arXiv