Privacy-Preserving Adversarial Representation Learning in ASR: Reality or Illusion?

By Brij Mohan Lal Srivastava, Aurélien Bellet, Marc Tommasi, Emmanuel Vincent. 2019

84 citations recorded by the source corpus.

Automatic speech recognition (ASR) is a key technology in many services and applications. This typically requires user devices to send their speech data to the cloud for ASR decoding. As the speech signal carries a lot of information about the speaker, this raises serious privacy concerns. As a solution, an encoder may reside on each user device which performs local computations to anonymize the representation. In this paper, we focus on the protection of speaker identity and study the extent to which users can be recognized based on the encoded representation of their speech as obtained by a deep encoder-decoder architecture trained for ASR. Through speaker identification and verification experiments on the Librispeech corpus with open and closed sets of speakers, we show that the representations obtained from a standard architecture still carry a lot of information about speaker identity. We then propose to use adversarial training to learn representations that perform well in ASR while hiding speaker identity. Our results demonstrate that adversarial training dramatically reduces the closed-set classification accuracy, but this does not translate into increased open-set verification error hence into increased protection of the speaker identity in practice. We suggest several possible reasons behind this negative result.

Subfields: Artificial Intelligence, Speech & Audio, Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Speech & Audio

In Privacy & Security

Citations in the corpus

Advances and Open Problems in Federated Learning (2019, methodology): “ons fair with respect to the attributes. In the centralized setting, one way to learn such representations is through adversarial training techniques, which have been applied to image and speech data [268, 164, 282, 60, 367]. In the federated learning scenario, clients could apply the transformation”