Search Results for author: Ingo Siegert

Found 7 papers, 1 papers with code

Pseudonymisation of Speech Data as an Alternative Approach to GDPR Compliance

no code implementations LEGAL (LREC) 2022 Pawel Kamocki, Ingo Siegert

The debate on the use of personal data in language resources usually focuses — and rightfully so — on anonymisation.

Public Interactions with Voice Assistant – Discussion of Different One-Shot Solutions to Preserve Speaker Privacy

no code implementations LEGAL (LREC) 2022 Ingo Siegert, Yamini Sinha, Gino Winkelmann, Oliver Jokisch, Andreas Wendemuth

Hereby, above all, the user’s speech data is stored and processed on a cloud platform, being the decisive factor for a good performance in speech processing and understanding.

Improving Voice Conversion for Dissimilar Speakers Using Perceptual Losses

no code implementations15 Sep 2023 Suhita Ghosh, Yamini Sinha, Ingo Siegert, Sebastian Stober

The rising trend of using voice as a means of interacting with smart devices has sparked worries over the protection of users' privacy and data security.

Speaker Verification Voice Conversion

Emo-StarGAN: A Semi-Supervised Any-to-Many Non-Parallel Emotion-Preserving Voice Conversion

1 code implementation14 Sep 2023 Suhita Ghosh, Arnab Das, Yamini Sinha, Ingo Siegert, Tim Polzehl, Sebastian Stober

Speech anonymisation prevents misuse of spoken data by removing any personal identifier while preserving at least linguistic content.

Voice Conversion

``Alexa in the wild'' -- Collecting Unconstrained Conversations with a Modern Voice Assistant in a Public Environment

no code implementations LREC 2020 Ingo Siegert

A specifically developed quiz was starting point of the conversation, as the voice assistant was presented to the visitors as a possible joker for the quiz.

Cross-Corpus Data Augmentation for Acoustic Addressee Detection

no code implementations WS 2019 Oleg Akhtiamov, Ingo Siegert, Alexey Karpov, Wolfgang Minker

Mixup is shown to be beneficial for merging acoustic data (extracted features but not raw waveforms) from different domains that allows us to reach a higher classification performance on human-machine AD and also for training a multipurpose neural network that is capable of solving both human-machine and adult-child AD problems.

Cross-corpus Data Augmentation +1

Towards Emotion and Affect Detection in the Multimodal LAST MINUTE Corpus

no code implementations LREC 2012 J{\"o}rg Frommer, Bernd Michaelis, Dietmar R{\"o}sner, Andreas Wendemuth, Rafael Friesen, Matthias Haase, Manuela Kunze, Rico Andrich, Julia Lange, Axel Panning, Ingo Siegert

The LAST MINUTE corpus comprises multimodal recordings (e. g. video, audio, transcripts) from WOZ interactions in a mundane planning task (R{\"o}sner et al., 2011).

Cannot find the paper you are looking for? You can Submit a new open access paper.