Michael Kuhlmann

Kontakt

Publikationen

Nachrichtentechnik (NT)

Wissenschaftlicher Mitarbeiter - Forschung & Lehre

VCard

Telefon:

+49 5251 60-3680

E-Mail:

kuhlmann(at)nt.upb(dot)de

Büro:

P7.2.06.1

Besucher:

Pohlweg 47-49
33098 Paderborn

Studienberatung Elektrotechnik (Studi.ET)

Mitglied - Wissenschaftlicher Mitarbeiter - Fachstudienberater Computer Engineering

VCard

Telefon:

+49 5251 60-3202

E-Mail:

studienberatung(at)ei.upb(dot)de

Büro:

P1.3.38

Web:

Homepage

Besucher:

Pohlweg 47-49
33098 Paderborn

Liste im Research Information System öffnen

2022

Investigation into Target Speaking Rate Adaptation for Voice Conversion

M. Kuhlmann, F. Seebauer, J. Ebbers, P. Wagner, R. Häb-Umbach, in: Interspeech 2022, ISCA, 2022

Download

DOI

https://www.isca-speech.org/archive/pdfs/interspeech_2022/kuhlmann22_interspeech.pdf

2021

Contrastive Predictive Coding Supported Factorized Variational Autoencoder for Unsupervised Learning of Disentangled Speech Representations

J. Ebbers, M. Kuhlmann, T. Cord-Landwehr, R. Haeb-Umbach, in: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, pp. 3860–3864

Abstract

Download

In this work we address disentanglement of style and content in speech signals. We propose a fully convolutional variational autoencoder employing two encoders: a content encoder and a style encoder. To foster disentanglement, we propose adversarial contrastive predictive coding. This new disentanglement method does neither need parallel data nor any supervision. We show that the proposed technique is capable of separating speaker and content traits into the two different representations and show competitive speaker-content disentanglement performance compared to other unsupervised approaches. We further demonstrate an increased robustness of the content representation against a train-test mismatch compared to spectral features, when used for phone recognition.

Template.pdf -

Liste im Research Information System öffnen