|
The 2nd ‘CHiME’ Speech Separation and Recognition Challenge: Approaches on single-channel speech separation and model-driven speech enhancement |
|
Signal Processing and Speech Communication (SPSC) Lab |
|
Demonstration of results obtained for 2nd CHiME Challenge |
|
Recovering a target speech signal from a multisource reverberant environment i.e. real-world conditions with acoustic clutter and fast varying noise sources is a challenging area of research. The 2nd CHiME challenge addressed the development of machine listening applications for operation in such an adverse noise scenarios. Here, we present the sound demonstration of speech separation and enhancement in highly non-stationary noisy environment, as presented by CHiME 2013 challenge. The data was provided by the 2nd CHiME challenge organization and the source separation and speech enhancement was done at Speech Communication and Signal Processing (SPSC) Lab, Technische Universität Graz (TU GRAZ). The related references are found at the bottom of this page.
References
[1] P. Mowlaee, J. A. Morales-Cordovilla, F. Pernkopf, H. Passentheiner, M. Hagmuller, and G. Kubin, "The 2nd ‘CHIME’ Speech Separation and Recognition Challenge: Approaches on Single-channel Speech Separation and Model-driven Speech Enhancement", in Proceeding of the 2nd CHiME Speech Separation and Recognition Challenge,", IEEE Int. Conf. Acoustics, Speech, Signal Processing, May. 2013, Vancouver, Canada, In Press .
[2] M. Stark, M. Wohlmayr, and F. Pernkopf, "Source-Filter based Single Channel Speech Separation using Pitch Information", IEEE Transactions on Audio, Speech and Language Processing, vol. 19, issue 2, pp. 242 - 255, Feb., 2011.
[3] P. Mowlaee, R. Saeidi, "Target Speaker Separation in a Multisource Environment Using Speaker-dependent Postfilter and Noise Estimation", IEEE Int. Conf. Acoustics, Speech, Signal Processing, May. 2013, Vancouver, Canada, In Press .
[4] P. Mowlaee, R. Saeidi, R. Martin, “Model-driven speech enhancement for multisource reverberant environment (Signal Separation Evaluation Campaign (SiSEC) 2011)”, Proceedings of the 10th International Conference on Latent Variable Analysis and Source Separation, LVA/ICA, 454-461, 2012. |
|
Development set
|
|
m6dB |
|
Observed speech |
|
m3dB |
|
0dB |
|
3dB
|
|
6dB |
|
9dB |
|
MD-SCSE |
|
SCSS |
|
s17_sbwt1a |
|
s10_sbwy4n |
|
s16_sbbs7p |
|
s22_sbbz6a |
|
s1_bris5a |
|
s3_pbwc7s |
|
spkr utterance |