Speaker de-identification via voice transformation

It is a common feature of modern automated voice-driven applications and services to record and transmit a user´s spoken request. At the same time, several domains and applications may require keeping the content of the user´s request confidential and at the same time preserving the speaker´s identity. This requires a technology that allows the speaker´s voice to be de-identified in the sense that the voice sounds natural and intelligible but does not reveal the identity of the speaker. In this paper we investigate different voice transformation strategies on a large population of speakers to disguise the speakers´ identities while preserving the intelligibility of the voices. We apply two automatic speaker identification approaches to verify the success of de-identification with voice transformation, a GMM-based and a phonetic approach. The evaluation based on the automatic speaker identification systems verifies that the proposed voice transformation technique enables transmission of the content of the users´ spoken requests while successfully preserving their identities. Also, the results indicate that different speakers still sound distinct after the transformation. Furthermore, we carried out a human listening test that proved the transformed speech to be both intelligible and securely de-identified, as it hid the identity of the speakers even to listeners who knew the speakers very well.