%Aigaion2 BibTeX export from Idiap Publications
%Wednesday 19 June 2024 12:39:32 AM

@ARTICLE{Dubagunta_CSL_2022,
         author = {Dubagunta, S. Pavankumar and van Son, Rob J. J. H. and Magimai.-Doss, Mathew},
       projects = {Idiap},
          month = mar,
          title = {Adjustable Deterministic Pseudonymization of Speech},
        journal = {Computer, Speech & Language},
         volume = {72},
           year = {2022},
           note = {Open Access},
           issn = {0885-2308},
            doi = {https://doi.org/10.1016/j.csl.2021.101284},
       crossref = {Dubagunta_Idiap-RR-12-2021},
       abstract = {While public speech resources become increasingly available, there is a growing interest to preserve the privacy of the speakers, through methods that anonymize the speaker information from speech while preserving the spoken linguistic content. In this paper, a method for pseudonymization (reversible anonymization) of speech is presented, that allows to obfuscate the speaker identity in untranscribed running speech. The approach manipulates the spectro-temporal structure of the speech to simulate a different length and structure of the vocal tract by modifying the formant locations, as well as by altering the pitch and speaking rate. The method is deterministic and partially reversible, and the changes are adjustable on a continuous scale. The method has been evaluated in terms of (i) ABX listening experiments, and (ii) automatic speaker verification and speech recognition. ABX experimental results indicate that the speaker identifiability among forced choice pairs reduced from over 90\% to less than 70\% through pseudonymization, and that de-pseudonymization was partially effective. An evaluation on the VoicePrivacy 2020 challenge data showed that the proposed approach performs better than the signal processing based baseline method that uses McAdams coefficient and performs slightly worse than the neural source filtering based baseline method. Further analysis showed that the proposed approach: (i) is comparable to the neural source filtering baseline based method in terms of phone posterior feature based objective intelligibility measure, (ii) preserves formant tracks better than the McAdams based method, and (iii) preserves paralinguistic aspects such as dysarthria in several speakers.}
}



crossreferenced publications: 
@TECHREPORT{Dubagunta_Idiap-RR-12-2021,
         author = {Dubagunta, S. Pavankumar and Van Son, Rob and Magimai.-Doss, Mathew},
       projects = {Idiap},
          month = {8},
          title = {Adjustable Deterministic Pseudonymization of Speech},
           type = {Idiap-RR},
         number = {Idiap-RR-12-2021},
           year = {2021},
    institution = {Idiap},
            pdf = {https://publications.idiap.ch/attachments/reports/2021/Dubagunta_Idiap-RR-12-2021.pdf}
}