This page demonstrates a sound separation method based on binaural cues extracted from the responses of a KEMAR dummy head. The system was systematically tested for multiple source configurations in anechoic conditions.
For more details see:
N. Roman, D. L. Wang and G. J. Brown, "Speech segregation based on sound localization," J. Acoust. Soc. Am., vol. 114, pp. 2236-2252, 2003.
Two-source configuration (Target at 0o ; Noise at 30o)
Noise | Mixture | Reconstructed target |
Pure Tone | ||
White Noise | ||
Noise Burst | ||
Cocktail Party | ||
Rock Music | ||
Siren | ||
Trill Telephone | ||
Female Speech | ||
Male Speech | ||
Female Speech |
Three-source configuration (Target at 0o; Noise 1 at -30o; Noise 2 at 30o)
Noise 2 | Mixture | Reconstructed target |
Pure Tone | ||
White Noise | ||
Noise Burst | ||
Cocktail Party | ||
Rock Music | ||
Siren | ||
Trill Telephone | ||
Female Speech | ||
Male Speech | ||
Female Speech |
Speech signals of the training set