M
Michael Pucher
Researcher at University of the Basque Country
Publications - 55
Citations - 892
Michael Pucher is an academic researcher from University of the Basque Country. The author has contributed to research in topics: Speech synthesis & Intelligibility (communication). The author has an hindex of 11, co-authored 49 publications receiving 828 citations.
Papers
More filters
Journal ArticleDOI
Evaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech
TL;DR: A new feature based on relative phase shift (RPS) is proposed, demonstrated reliable detection of synthetic speech, and shown how this classifier can be used to improve security of SV systems.
Proceedings ArticleDOI
Detection of synthetic speech for the problem of imposture
TL;DR: A HMM-based speech synthesizer is used, which creates synthetic speech for a targeted speaker through adaptation of a background model and both GMM-UBM and support vector machine (SVM) SV systems are used, reducing the vulnerability of a speaker verification (SV) system to synthetic speech.
Evaluation of the Vulnerability of Speaker Verification to Synthetic Speech
TL;DR: While SV systems have impressive accuracy, even with the proposed detector, high-quality synthetic speech can lead to an unacceptably high acceptance rate of synthetic speakers.
Journal ArticleDOI
Modeling and interpolation of Austrian German and Viennese dialect in HMM-based speech synthesis
TL;DR: Good evaluation results show that listeners can perceive both continuous and categorical changes of dialect varieties by using phonological transformations employed as switching rules in the HMM interpolation.
Proceedings ArticleDOI
Revisiting the security of speaker verification systems against imposture using synthetic speech
TL;DR: Overall, while SV systems have impressive accuracy, even with the proposed detector, high-quality synthetic speech will lead to an unacceptably high false acceptance rate.