In the following you will find the prelimnary prgoram of ESSV 2021.
March 3rd
From | To | Program |
8:45 | 9:00 | Entrance |
9:00 | 9:30 | Opening and Greeting |
9:30 | 10:30 | Keynote 1: Hans Uszkoreit |
10:30 | 12:00 | Session 1: Paralinguistics
Ingo Siegert, Oliver Niebuhr OVGU Magdeburg Speech Signal Compression Deteriorates Acoustic Cues to Perceived Speaker Charisma Anabell Hacker TU Berlin ‚Alexa, who are you?‘ – Analysing Alexa's, Cortana's and Siri's Vocal Personality Siddarth Venkateswaran, Thomas Keßler, Ronald Böck, Ossmane Krini OVGU Magdeburg Pseudo-Labelling and Transfer Learning Based Speech Emotion Recognition Lara-Sophie Christmann TU Berlin Emotion Bias in Automatic Speech Recognition |
12:00 | 13:30 | Lunch break |
13:30 | 14:30 | Poster Session 1
Felix Burkhardt, Markus Brückl, Björn W. Schuller TU Berlin Age classification: Comparison of Human and Machine Performance Using Different Utterance Types Ivan Kraljevski, Marek Rjelka, Frank Duckhorn, Constanze Tschöpe, Matthias Wolff BTU Cottbus-Senftenberg Cross-Lingual Acoustic Modeling in Upper Sorbian - Preliminary Study Janina Reuter, Merikan Koyun, Christoph Daniel Schulze, Reinhard von Hanxleden CAU Kiel Real-Time Implementation, Comparison, and Combination of pitch tracking Algorithms Jürgen Trouvain, Raphael Werner Universität des Saarlandes Human pause detection in spontaneous speech in an online experiment Werner Meyer, Borislav Borislavov, Friedrich Eckert, Christian Richter, Ronald Römer, Peter beim Graben, Markus Huber, Matthias Wolff BTU Cottbus-Senftenberg Formalisierung und Implementierung einer adaptiven kognitiven Architektur unter Verwendung von Strukturdiagrammen Oliver Jokisch, Tilo Strutz, Alexander Leipnitz, Ingo Siegert, Andrey Ronzhin HfT Leipzig Audio and Video Processing of UAV-Based Signals in the Harmonic Project Mino Lee Sasse, Stefan Schaffer, Aaron Ruß DFKI Berlin Automatic-Subtitling, Comparison on the Performance of Forced Alignment and Automatic Speech Recognition Sebastian Barth, Simon Stone, Peter Birkholz TU Dresden Artificial Bandwidth Extension using a Glottal Excitation Model |
14:30 | 14:45 | Coffee break |
14:45 | 16:15 | Session 2: ASR
Wentao Yu, Steffen Zeiler, Dorothea Kolossa Ruhr-Universität Bochum Towards reliability-guided information integration in audio-visual speech recognition Pouriya Amini Digehsara, Christoph Wagner, Petr Schaffer, Michael Bärhold , Simon Stone, Dirk Plettemeier, Peter Birkholz TU Dresden On the optimal set of features and robustness of classifiers in radar-based silent phoneme recognition Fahrettin Gökgöz, Mahmoud Hashem Fraunhofer FKIE Investigating the scarce data and resources problem for speech recognition using transfer learning and data augmentation Benjamin Milde, Robert Geislinger, Irina Lindt, Timo Baumann Universität Hamburg Open source automatic lecture subtitling |
17:00 | 19:00 | Welcome Reception in gather.town
Panel discussion "Nachwuchs in der Sprachtechnologie aus Sicht der Wirtschaft" Invited guests:
|
19:00 | Meeting of the Förderverein |
March 4th
From | To | Program |
8:45 | 9:00 | Entrance |
9:00 | 10:00 | Keynote 2: Elisabeth André |
10:00 | 12:00 | Session 3: Phonetics/Articulation
Harald Höge Universität der Bundeswehr München Cortical Segmentation of Syllables Paul Konstantin Krug, Simon Stone, Alexander Wilbrandt, Peter Birkholz TU Dreden TargetOptimizer 2.0: Enhanced Estimation of Articulatory Targets B. Andreeva, G. Demenko, J. Bachan, I. Gessinger, K. Jankowska, B. Möbius Universität des Saarlandes Phonetic convergence evaluation based on fundamental frequency variability Peter Steiner, Ian S. Howard, Peter Birkholz TU Dresden Glottal Closure Instant Detection using Echo State Networks Ian S. Howard, Julian McGlashan & Adrian J. Fourcin University of Plymouth Machine Learning analysis of speech and EGG for the diagnosis of voice pathology Paul Schmidt-Barbo, Elnaz Shafaei-Bajestan, Konstantin Sering Eberhard Karls Universität Tübingen Predictive articulatory speech synthesis with semantic discrimination |
12:00 | 13:30 | Lunch break |
13:30 | 14:30 | Poster Session 2
Omnia Ibrahim, Ivan Yuen, Marjolein van Os, Bistra Andreeva, Bernd Möbius Universität des Saarlandes The effect of Lombard speech modifications in different information density contexts Benjamin Weiss, Stefan Hillmann, Sebastian Möller TU Berlin Intents in Sprachdialogen: Eine Praxisperspektive Thomas Ranzenberger, Christian Hacker Elektrobit Automotive GmbH, Erlangen VADiMoS: A Web Tool For Designing Voice Assistant Independent and Ontology based Dialogs Konstantin Sering, Motoki Saito, Fabian Tomaschek Eberhard Karls Universität Tübingen Anticipatory coarticulation in predictive articulatory speech modeling Alexandra Ebel, Johannes Förster, Mathias Walther Martin-Luther-Universität Halle-Wittenberg Developing the German Pronunciation Database (DAD) - an online dictionary for spoken German Marco Braune TU Berlin Untersuchung von Qualitätsunterschieden zwischen gesprochener und geschriebener Sprache bei Interaktion mit einem Chatbot Daniel Duran, Sarah Warchhold Albert-Ludwigs-Universität Freiburg Der Faktor Mensch in der Mensch-Maschine-Interaktion |
14:30 | 14:45 | Coffee break |
14:45 | 16:15 | Session 4: Speech dialog
Stefan Hillmann, Tilo Himmelsbach, Benjamin Weiss TU Berlin Performanz und Trainingsverhalten von Dialog-Policies bei Reinforcement Learning Md. Mahmud-uz-zaman, Stefan Schaffer, Tatjana Scheffler DFKI Berlin Comparing BERT with an intent based question answering setup for open-ended questions in the museum domain Peter Klimczak, Peter beim Graben, Markus Huber, Günther Wirsching BTU Cottbus A Dynamic Machine Semiotics Approach for a Human-Centered User Interface Jan Nehring, Akhyar Ahmed DFKI Berlin Normalisierungsmethoden für Intent Erkennung Modularer Dialogsysteme |
March 5th
From | To | Program |
8:45 | 9:00 | Entrance |
9:00 | 10:00 | Keynote 3: David Schlangen |
10:00 | 11:00 | Session 5: Synthesis
Jacek Kudera, Marjolein van Os, Bernd Möbius Universität des Saarlandes Natural and synthetic speech comprehension in simulated tonal and pulsatile tinnitus: A pilot study Bogdan Ludusan, Petra Wagner Universität Bielefeld Knock-Knock! Who's There? The Laughter-Enhanced Virtual Real-Estate Agent Mikey Elmers, Raphael Werner, Bernd Möbius, Jürgen Trouvain Universität des Saarlandes Evaluating the effect of pauses on number recollection in synthesized speech |
11:00 | 11:30 | Coffee break |
11:30 | 12:30 | Session 6: Speech signal processing / evaluation
Sebastian Möller, Andreas Bütow TU Berlin Prediction of Background Noise Degradations in Fulland Speech Communication Scenarios Georg Schmidt, Ingo Siegert OVGU Magdeburg Studie zur Lösbarkeit des Problems starker Pegelschwankungen im Home-Entertainment Thilo Michael TU Berlin Intelligibility in Telephone Conversations with Packet Loss |
12:30 | 13:30 | Announcement of ESSV 2022 Best Student Paper award ceremony Closing |