Vocoder drift compensation by x-vector alignment in speaker anonymisation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 21 references that are in the map. First posted on arXiv 17 Jul 2023.
Builds on
16 of 21 references.
References · 16
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
- 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 639
- 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 606
- 2021A Comparison of Discrete and Soft Speech Units for Improved Voice Conversioncited by 61
- 2020Introducing the VoicePrivacy Initiativecited by 48
- 2021The VoicePrivacy 2020 Challenge: Results and findingscited by 45
- 2019Speaker Anonymization Using X-vector and Neural Waveform Modelscited by 41
- 2022Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacycited by 20
- 2022The VoicePrivacy 2022 Challenge Evaluation Plancited by 18
- 2022Differentially Private Speaker Anonymizationcited by 16
- 2022Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Modelscited by 14
4 more
- 2022Are disentangled representations all you need to build speaker anonymization systems?cited by 10
- 2021A Study of F0 Modification for X-Vector Based Speech Pseudonymization Across Gendercited by 9
- 2022VoicePrivacy 2022 System Description: Speaker Anonymization with Feature-matched F0 Trajectoriescited by 3
- 2023Vocoder drift in x-vector-based speaker anonymizationcited by 2
Built on by
Citing papers per year: 2025: 1.
1 paper.