Sehr geehrte Abonnenten des Kolloquium-Newsletters,

gerne informieren wir Sie über die nächsten Termine unseres Kommunikationstechnischen Kolloquiums.

Mittwoch, 5. Juni 2019
Vortragender: Andreas Behler
Ort: Hörsaal 4G IKS
Zeit: 11:15 Uhr

Master-Vortrag: Investigations on the Translational Displacement within a Higher Order Ambisonics Sound Field Representation

With the advance of video recordings in the field of six degrees of freedom, the audio recordings have to adapt. The availability of spherical microphone arrays and a growing research interest make Ambisonics an attractive tool and its possible ability to facilitate soundfield navigation is intriguing.

This thesis explored a way to enable a position change within higher order Ambisonics recording with a single spherical microphone array. For this a parametric decomposition of the recorded sound field was used based on the coding and multidirectional parametrisation of Ambisonic sound scenes method. With it an algorithm was developed with the ability to adjust the loudness and rotate primary signal parts to compute a translational shift. As a prerequisite the algorithm needs distance information of the recorded scene. Furthermore, a way to adapt to differently conditioned signals was developed. It was evaluated along with the proposed algorithm in a realistic surrounding with objective measurements.

For a subjective impression a listening test was conducted with 31 participants using a spherical loudspeaker setup. The objective and subjective tests included a comparison to higher oder Ambisonics warping, a zooming method for Ambisonics. The evaluations of both tests returned positive results.

und

Donnerstag, 6. Juni 2019
Vortragender: Marcel Czaplinski
Ort: Hörsaal 4G IKS
Zeit: 11:15 Uhr

Master-Vortrag: Machine Learning Techniques to Reconstruct Lost Parts of Speech Signals

Applications for Speech transmission and mobile communication have high demands for speech intelligibility and authenticity. Errors and corruptions of different types are commonly occuring. Often, parts of the speech signal are missing completely.

A major task in speech processing and transmission is the enhancement of a speech signal and minimizing distortions that occur as a result of corruptions. If the distorted signal parts of the speech signal cannot be restored, they can be dropped completely and reconstructed to a certain degree from the uncorrupted parts of the signal. This technique is the core idea of the well-known packet loss concealment (PLC) and bandwidth extension (BWE). However, these tools assume the missing parts to be of time or frequency limited shape.

Speech inpainting, the task of the reconstruction of lost parts of a speech signal of any shape, extends BWE and PLC to a generalized concept. Some dictionary based speech inpainters have been proposed from various researchers in the past. Despite the progress and promising results of recent machine learning research from related topics like image inpainting, not many endeavours have been made to use signal processing and machine learning jointly to build speech inpainters.

A general framework and overview of a machine learning assisted speech inpainter will be provided. A selection of preprocessing tools and algorithms will be analyzed in the context of different corruption types and the results compared to a simple interpolation algorithm. Furthermore, time and frequency interpolation capabilities of algorithms and speech features will become interpretable and new insights into existing problems will be granted.

Alle Interessierten sind herzlich eingeladen, eine Anmeldung ist nicht erforderlich.

Allgemeine Informationen zum Kolloquium, sowie eine aktuelle Liste der Termine des Kommunikationstechnischen Kolloquiums finden Sie unter:
http://www.iks.rwth-aachen.de/aktuelles/kolloquium/

-- 
Irina Ronkartz
Institute of Communication Systems (IKS)
RWTH Aachen University
Muffeter Weg 3a, 52074 Aachen, Germany
+49 241 80 26958 (phone)
ronkartz@iks.rwth-aachen.de
http://www.iks.rwth-aachen.de/