ITG – Informationstechnische Gesellschaft im VDE (ITG) (Ed.)

ITG-Fb. 282: Speech Communication

13. ITG-Fachtagung Sprachkommunikation 10. – 12. Oktober 2018 in Oldenburg

ITG-Fachberichte

2018, 352 pages, Slimlinebox, CD-Rom
ISBN 978-3-8007-4767-2
Personal VDE Members are entitled to a 10% discount on this title

Content Foreword

The 13th ITG conference on Speech Communication solicits contributions on theory, algorithms, and applications in the following areas of speech, audio, and spoken language processing:
• Speech Enhancement and Separation
• Source Localization and Tracking
• Automatic Speech and Speaker Recognition
• Spoken Dialogue, Diarization, and Spoken Document Retrieval Systems
• Speech Synthesis
• Speech Modeling, Coding, and Transmission
• Speech Production and Perception
• Speech and Audio Quality Assessment
• Speech Intelligibility Assessment
• Paralinguistics, speech diagnostics and speech-related biosignals
• Speech in Automotive, Mobile, and Multimodal Applications
• Acoustic Interfaces, Assistive Devices, and Hearing Aids
• Hardware and Software Tools
• Emerging Topics and Applications
Die ITG ist die nationale Vereinigung aller auf dem Gebiet der Informationstechnik Tätigen in Wirtschaft, Verwaltung, Lehre und Forschung und Wissenschaft. Ihre Ziele sind die Förderung der wissenschaftlichen und technischen Weiterentwicklung und Bewertung der Informationstechnik in Theorie und Praxis. 1954 als Nachrichtentechnische Gesellschaft gegründet, ist sie die älteste Fachgesellschaft im VDE.

1

Signal Processing Challenges for Active Noise Cancellation Headphones

Authors:
Liebich, Stefan; Fabry, Johannes; Jax, Peter; Vary, Peter
2

Hybrid Active Noise Control Structures: A Short Overview

Authors:
Rivera Benois, Piero; Nowak, Patrick; Zoelzer, Udo
3
4
5

A Relative-Transfer-Function-based Post-Filter for Speech Enhancement in Hearing Aids using a Nearby External Microphone

Authors:
Yee, Dianna; Kamkar-Parsi, Homayoun; Martin, Rainer; Puder, Henning
6

Multi-loudspeaker equalization for acoustic transparency in a custom hearing device

Authors:
Schepker, Henning; Denk, Florian; Kollmeier, Birger; Doclo, Simon
7

On the Benefit of a Stereo Acoustic Echo Cancellation in an In-Car Communication System

Authors:
Franzen, Jan; Meyer zum Alten Borgloh, Inka; Fingscheidt, Tim
8
9

Automatic Screening for Transition into Dementia using Speech

Authors:
Weiner, Jochen; Schultz, Tanja
10

Evaluation of the Pain Level from Speech: Introducing a Novel Pain Database and Benchmarks

Authors:
Ren, Zhao; Cummins, Nicholas; Han, Jing; Schnieder, Sebastian; Krajewski, Jarek; Bjoern Schuller
11

On the Effects of Speaker Gender in Emotion Recognition Training Data

Authors:
Xu, Ziyi; Meyer, Patrick; Fingscheidt, Tim
12

A comparison of EMG-to-Speech Conversion for Isolated and Continuous Speech

Authors:
Diener, Lorenz; Bredehoeft, Sebastian; Schultz, Tanja
13

DNN/CNN Acoustic Model Turbo Fusion for Phoneme Recognition

Authors:
Lohrenz, Timo; Li, Wei; Fingscheidt, Tim
14

Sequence Modeling and Alignment for LVCSR-Systems

Authors:
Beck, Eugen; Zeyer, Albert; Doetsch, Patrick; Merboldt, Andre; Schlueter, Ralf; Ney, Hermann
15
16

Objective Assessment of a Speech Enhancement Scheme with an Automatic Speech Recognition-Based System

Authors:
Huber, Rainer; Pusch, Arne; Moritz, Niko; Rennies, Jan; Schepker, Henning; Meyer, Bernd T.
17

Resource Allocation for Distributed Blind Source Separation

Authors:
Bachmann, Markus; Brendel, Andreas; Kellermann, Walter
18
19
20
21
22

Signal-based Root Cause Analysis of Quality Impairments in Speech Communication Networks

Authors:
Huebschen, Tobias; Mittag, Gabriel; Moeller, Sebastian; Schmidt, Gerhard
23

Perceived Listening Effort for In-car Communication systems

Authors:
Reimes, Jan; Lueke, Christian
24

Robust DNN-Based Speech Enhancement with Limited Training Data

Authors:
Rehr, Robert; Gerkmann, Timo
25

Smoothing along Frequency in Online Neural Network Supported Acoustic Beamforming

Authors:
Heitkaemper, Jens; Heymann, Jahn; Haeb-Umbach, Reinhold
26

Multichannel Nonnegative Matrix Factorization for Ego-Noise Suppression

Authors:
Haubner, Thomas; Schmidt, Alexander; Kellermann, Walter
27
28

Subband Based Room Impulse Response Reshaping

Authors:
Mazur, Radoslaw; Katzberg, Fabrice; Böhme, Martina; Mertins, Alfred
29

Good Noise Power Estimators Are Not Always Good

Authors:
Meyer, Patrick; Elshamy, Samy
30
31

Evaluation of binaural Own Voice Detection (OVD) algorithms

Authors:
Bitzer, Joerg; Bilert, Sascha; Holube, Inga
32

Distributed MAP Estimators for Noise Reduction in Fully Connected Wireless Acoustic Sensor Networks

Authors:
Ranjbaryan, Raziyeh; Doclo, Simon; Abutalebi, Hamid Reza
33

Benchmarking Neural Network Architectures for Acoustic Sensor Networks

Authors:
Ebbers, Janek; Heitkaemper, Jens; Schmalenstroeer, Joerg; Haeb-Umbach, Reinhold
34

Unsupervised Domain Adaptation by Adversarial Learning for Robust Speech Recognition

Authors:
Denisov, Pavel; Vu, Ngoc Thang; Ferras Font, Marc
35

Parameter Optimization for CTC Acoustic Models in a Less-resourced Scenario: An Empirical Study

Authors:
Mueller, Markus; Stueker, Sebastian; Waibel, Alex
36

Keyword Detection for the Activation of Speech Assistants

Authors:
Hirsch, Hans-Guenter; Gref, Michael
37

Utilizing Slow Feature Analysis for Lipreading

Authors:
Freiwald, Jan; Karbasi, Mahdie; Zeiler, Steffen; Melchior, Jan; Kompella, Varun; Wiskott, Laurenz; Kolossa, Dorothea
38

Diagnostic and Summative Approach for Predicting Speech Communication Quality in a Super-Wideband Context

Authors:
Moeller, Sebastian; Huebschen, Tobias; Mittag, Gabriel; Schmidt, Gerhard
39
40
41

Enhancement of G.711-Coded Speech Providing Quality Higher Than Uncoded

Authors:
Zhao, Ziyue; Liu, Huijun; Fingscheidt, Tim
42

NARA-WPE: A Python package for weighted prediction error dereverberation in Numpy and Tensorflow for online and offline processing

Authors:
Drude, Lukas; Heymann, Jahn; Boeddeker, Christoph; Haeb-Umbach, Reinhold
43
44

Equalization filter design for achieving acoustic transparency in a semi-open fit hearing device

Authors:
Denk, Florian; Schepker, Henning; Doclo, Simon; Kollmeier, Birger
45

A gaze-based attention model for spatially-aware hearing aids

Authors:
Grimm, Giso; Kayser, Hendrik; Hendrikse, Maartje; Volker Hohmann,
46

Evaluation of Signal-Dependent Partial Noise Estimation Algorithms for Binaural Hearing Aids

Authors:
Klug, Jonas; Marquardt, Daniel; Goessling, Nico; Doclo, Simon
47
48

Insights into the Interplay of Sampling Rate Offsets and MVDR Beamforming

Authors:
Schmalenstroeer, Joerg; Haeb-Umbach, Reinhold
49

Open Source Automatic Speech Recognition for German

Authors:
Milde, Benjamin; Koehn, Arne
50
51

Robust Speaker Identification by Fusing Classification Scores with a Neural Network

Authors:
Wilkinghoff, Kevin; Baggenstoss, Paul M.; Cornaggia-Urrigshardt, Alessia; Kurth, Frank
52
53
54

Session-Independent Array-Based EMG-to-Speech Conversion using Convolutional Neural Networks

Authors:
Diener, Lorenz; Felsch, Gerrit; Angrick, Miguel; Schultz, Tanja
55
56
57

Acoustic Howling Detection and Suppression for IP-Based Teleconference Systems

Authors:
Kuehl, Stefan; Anemueller, Carlotta; Antweiler, Christiane; Jax, Peter; Heese, Florian; Vicinus, Patrick
58
59
60
61

MARVELO – A Framework for Signal Processing in Wireless Acoustic Sensor Networks

Authors:
Afifi, Haitam; Schmalenstroeer, Joerg; Ullmann, Joerg; Haeb-Umbach, Reinhold; Karl, Holger
62

Source separation by fuzzy-membership value aware beamforming and masking in ad hoc arrays

Authors:
Gergen, Sebastian; Martin, Rainer; Madhu, Nilesh
63

Densely Connected Convolutional Networks for Speech Recognition

Authors:
Li, Chia Yu; Vu, Ngoc Thang
64
65
66

Automatic Estimation of the Triangular Vowel Space Area from i-Vectors

Authors:
Tanuadji, Maureen; Stadtschnitzer, Michael; Bardeli, Rolf; Jaeger, Hagen
67

ANN-based Alzheimer’s disease classification from bag of words

Authors:
Klumpp, Philipp; Fritsch, Julian; Noeth, Elmar
68