Some Trials of Blind Source Separation

We are going to show some results of our experiments on Blind Source Separation. In every experiment, the number of the inputs and the outputs is 2. The following files are all stereo sound files. Left channel and right channel correspond to the inputs to the microphne 1 and microphne 2, respectively. We have a draft ("TR1998-2.pdf", 2120k, last updated on 17 April, 1998) of a paper and if you are interested in these results, please read it. We also provide matlab codes, and C codes.

I. Signals Mixed on Computer

These examples are artificially mixed on DEC Alpha station 200 after recording each source signal separately. For the detail, please go to the description page.

1. Instantaneous mixtures

2. Convolutive mixtures I

3. Convolutive mixtures II (in a virtual room)

II. Signals from Dr. Te-Won Lee's Home Page

These examples are taken from Dr. Te-Won's Home page at the Salk Institute. So, for the detail of the signals, please take a look at Dr. Te-Won's page. And also, in order to see their results, please refer to Dr. Te-Won's page.

1. Speech - Music Separation

2. Speech - Speech Separation

3. Speech - Speech Separation in difficult environments

III. Signals from Mr. Paris Smaragdis' Home Page

This example is taken from Mr. Paris Smaragdis' Home Page at the MIT Media Lab. So, for the detail of the signals, and to see their results, please visit his page.

IV. Signals from Prof. Kota Takahashi

These data were given by Prof. Kota Takahashi(Japanese only) in the University of Electro-Communication.

1. Speech - Speech Separation in difficult environments

These data were recorded in a real environment.

2. Speech - Speech Separation in difficult environments

This data were also recorded in the same lab. But they include more reflections.

V. Signals from Dr. Mark Girolami

Dr. Mark Girolami gave me some data, and I used them for experiments.

1. Speech - Speech

These data were recorded in a real environment.

2. Speech - Noise (Gaussian)

3. Speech - Noise (Laplace)

4. Speech - Noise (Gaussian)

5. Speech - Noise (Laplace)

VI. Online Learning Algorithm

These examples are artificially mixed on DEC Alpha station 200 after recording each source signal separately.

1. Online Learning