Elektronische Sprachsignalverarbeitung


Conference Programme

A printed version of the programme will be provided.

Wednesday, March 4, 2020

Time Title Authors
12.30 - 13.00  Opening Ceremony
13.00 - 14.00 Keynote: Sprachtechnologien für digitale Assistenten Reinhold Häb-Umbach (Chair: A. Wendemuth)
14.00 - 15.00 Session: (Speech) Assistents Chair: I. Siegert
14.00 - 14.20 Keyword Detection for the Activation of Speech Dialogue Systems Hans-Günter Hirsch, Alexander Micheel, Michael Gref
14.20 - 14.40 Increasing Industrial Productivity by Employing a Smart Speech-Based Question Answering Assistant Bojan Kovachki, Aleksandar Gjoreski, Robert Herms, Matthias Pohl, Martin Wenzel, Frank Seifert, Diane Hirschfeld
14.40 - 15.00 User Acceptance of Proactive Voice Assistant Behavior Maria Schmidt, Wolfgang Minker, Steffen Werner
15.00 - 15.30 Coffee Break
15.30 - 17.00 Session: Speech Synthesis Chair: R. Hoffmann
15.30 - 15.50 Überlegungen zu wahrnehmbaren Lächeln in synthetischen Stimmen Jürgen Trouvain, Benjamin Weiss
15.50 - 16.10 Tongue Mouse - Comparison of Physical Measurement Principles Kathleen Große, Peter Birkholz
16.10 - 16.30 Speech Fundamental Period Estimation using a Neural Network Ian S. Howard
16.30 - 16.50 Articulatory Copy Synthesis using Long-Short Term Memory Networks Yingming Gao, Peter Steiner, Peter Birkholz
17.00 - 19.00 Welcome Reception
19.00 Sitzung ESSV Förderverein

Thursday, March 5, 2020

Time Title Authors
09.00 - 10.00  Keynote: Human-Computer Interaction closer to the Body Michael Beigl (Chair: R. Böck)
10.00 - 11.00 Session: (Speech) Signal Processing in Medical Applications Chair: C. Neuschäfer-Rube
10.00 - 10.20 Contactless Measurement of Heart Sounds and Heart Rate with
Laser Doppler Vibrometry
Kristian Kroschel, Armin Luik, Jürgen Metzler
10.20 - 10.40 A Hearing Aid to Visualize the Direction of Sound Udo Gebelein, Stefan Rapp
10.40 - 11.00 Comparing KEC Recordings with Resynthesized EMA Data Konstantin Sering, Fabian Tomaschek
11.00 - 11.30 Coffee Break
11.30 - 12.30 Session: Paralinguistics Chair: R. Böck
11.30 - 11.50 Hesitation processing analysis using mouse-tracking and
Simon Betz, Éva Székely, Sina Zarrieß, Marin Schröer, Leonie Schade, Petra Wagner
11.50 - 12.10 Simulating Turn-Taking in Conversations with Varying Interactivity Thilo Michael, Sebastian Möller
12.10 - 12.30 Ein sprachübergreifender Vergleich des Pausenverhaltens natürlicher Sprecher in verschiedenen Sprechtempi mit TTS-Systemen Raphael Werner, Jürgen Trouvain, Bernd Möbius
12.30 - 14.00 Lunch Break
14.00 - 15.00 Session: Acoustic Signals Chair: R. Römer
14.00 - 14.20 Low-Complexity Postfilter using MDCT-Domain for Speech and Audio
Sneha Das, Tom Bäckström
14.20 - 14.40 Towards a Robust Analysis and Classification of Dog Barking Maja Schneider, Oliver Jokisch
14.40 - 15.00 Spoken Language Identification by Means of Acosutic Mid-level Descriptors Uwe D. Reichel, Andreas Triantafyllopoulos , Christopher Oates, Stephan Huber, Björn Schuller
15.00 - 15.40 Session: Articulation Chair: J. Trouvain
15.00 - 15.20 The Nature of the Articulatory Code Harald Höge
15.20 - 15.40 Comparison of the French and German articulatory spaces Antoine Serrurier, Christiane Neuschaefer-Rube
15.40 - 16.00 Coffee Break
15.40 - 17.00 Poster Session Chair: K. Fellbaum
17.30 - 19.00 Guided Tour
19.30 - 23.00 Conference Dinner

Friday, March 6, 2020

Time Title Authors
09.00 - 10.00 Keynote: Listening through a Cochlear Implant Jesko L. Verhey (Chair: I. Siegert)
10.00 - 11.00 Session: Dialogue Chair: A. Wendemuth
10.00 - 10.20 Zur Automatischen Schätzung von Kostenfunktionen aus Dialogen Benjamin Weiss, Stefan Hillmann, Thilo Michael, Tilo Himmelsbach
10.20 - 10.40 Does Users' System Evaluation Influence Speech Behavior in HCI? - First Insights from the Engineering and Psychological Perspective Ingo Siegert, Matthias Busch, Julia Krüger
10.40 - 11.00 Vergleichende Untersuchung von Reinforcement Learning Verfahren beim Training eines Dialog Managers Stefan Hillmann, Tilo Himmelsbach, Benjamin Weiss
11.00 - 11.30 Coffee Break
11.30 - 12.30 Session: Quality Chair: B. Weiß
11.30 - 11.50 Einflussfaktoren auf die Wahrnehmung von Prominenz im natürlichen Dialog David Meier, Bistra Andreeva
11.50 - 12.10 "Space fighters" on stage - How the F1 and F2 vowel-space dimensions contribute to perceived speaker charisma Oliver Niebuhr
12.10 - 12.30 Relationship Between Root Causes of Impairments and Perceptual Quality Dimensions of Super-wideband Transmitted Speech Sebastian Möller, Tobias Hübschen, Gabriel Mittag, Gerhard Schmidt
12.30 - 13.00 Closing Ceremony and Farewell

Poster Session

Title Authors
Reduction of Aircraft Noise in UAV-Based Speech Signal Recordings by Quantile Based Noise Estimation Enrico Lösch, Oliver Jokisch, Alexander Leipnitz, Ingo Siegert
Note Onset Detection using Echo State Networks Peter Steiner, Simon Stone, Peter Birkholz
How to Identify Speech when Translating Unpunctuated Poetry Timo Baumann, Burkhard Meyer-Sickendiek , Hussein Hussein
Die Welt ist nicht genug! Man muss auch über sie sprechen können Ronald Römer, Peter beim Graben, Markus Huber, Peter Klimczak,
Günther Wirsching, Matthias Wolff
Rule-Based Dialog Management for Voice Assistents in Automotive Environments Soyuj Kumar Sahoo, Timo Sowa, Christian Hacker, Thomas
Speaker Gender Classification based on an Improved Deep Learning Approach Mohamed anouar Ben messaoud, Aicha Bouzid
Machine Learning-Assisted Affect Labelling of Speech Data Alicia F. Requardt, Olga Egorow, Andreas Wendemuth
Emergency Service – Sprachbasierte Klassifikation eingehender Anrufe in Ausnahmesituationen Marcus Petersen, Karl-Heinz Niedrist, Matthias Busch, Florian
Marquardt, Ingo Siegert
Uneindeutigkeiten in minimalistischen Grammatiken für Zahlworte – Probleme und Lösungsansätze Mira Schielke, Henriette Heinrich
Filtering-Based Analysis of Spectral and Temporal Effects of Room Modes on Low-Level Descriptors of Emotionally Coloured Speech Martin Gottschalk, Juliane Höbel-Müller, Ingo Siegert, Jesko Verhey and Andreas Wendemuth

Organised by:

Sponsored by:

By Ulrich Arendt.

ESSV 2020

By Ulrich Arendt.