Signal Enhancement for the SPID Corpus

In order to cancel the noise introduced by the ambiance simulation, an adaptive filter based noise cancellation algorithm was applied to the recordings of the SPID corpus. Furthermore, a frequency-domain noise and cross-talk suppression was applied. The two time and time-frequency pots below show examples. The enhanced as well as the original signals are available for the entire corpus parts where the ambiance simualtion was used.

 

Original Recording

 

Enhanced Recording

Contact

Prof. Dr.-Ing. Gerhard Schmidt

E-Mail: gus@tf.uni-kiel.de

Christian-Albrechts-Universität zu Kiel
Faculty of Engineering
Institute for Electrical Engineering and Information Engineering
Digital Signal Processing and System Theory

Kaiserstr. 2
24143 Kiel, Germany

How to find us

Recent News

TensorFlow and Escape Rooms

The last two days (Monday and Tuesday, September 16 and 17, 2019), the whole DSS team did a course on TensorFlow and Keras. Since we already have interfaces of TensorFlow to our real-time tool KiRAT, it was time now to extend our knowledge on graphs and the corresponding training of weights, biases, etc. After two days of hard work we booked two escape rooms and solved the "secrets" hidden in ...


Read more ...