Vocoder drift compensation by x-vector alignment in speaker anonymisation
This addresses a specific bottleneck in speaker anonymization systems for privacy applications, but it is incremental as it focuses on compensation rather than a new paradigm.
The paper tackled the problem of vocoder drift in speaker anonymization, where vocoding contributes more to anonymization than the core function, and showed that drift arises from mismatches between substituted x-vectors and original linguistic features. The result was a compensation method that reduced drift substantially, offering improved control over the x-vector space.
For the most popular x-vector-based approaches to speaker anonymisation, the bulk of the anonymisation can stem from vocoding rather than from the core anonymisation function which is used to substitute an original speaker x-vector with that of a fictitious pseudo-speaker. This phenomenon can impede the design of better anonymisation systems since there is a lack of fine-grained control over the x-vector space. The work reported in this paper explores the origin of so-called vocoder drift and shows that it is due to the mismatch between the substituted x-vector and the original representations of the linguistic content, intonation and prosody. Also reported is an original approach to vocoder drift compensation. While anonymisation performance degrades as expected, compensation reduces vocoder drift substantially, offers improved control over the x-vector space and lays a foundation for the design of better anonymisation functions in the future.