Skip to main content
EURASIP Journal on Advances in Signal Processing
Figure 4 | EURASIP Journal on Advances in Signal Processing

Figure 4

From: Rate-constrained source separation for speech enhancement in wireless-communicated binaural hearing aids

Figure 4

Time-frequency footprint selection. (a) SNR = 0 dB, (b) SNR = 3 dB and (c) SNR = 5 dB. Description: average WDO value obtained by the non-quantified classifier with the selected combination of features varying the number of neighbor frequencies (Nfreqs) and previous time frames (Nframes) of the time-frequency footprint. The different values of Nframes are represented with lines of different colors and the different values of Nfreqs with squares over the lines.

Back to article page