Single-channel dereverberation by feature mapping using cascade neural networks for robust distant speaker identification and speech recognition

EURASIP Journal on Audio, Speech, and Music Processing

Table 1 Speaker identification baseline for each type of simulated (noisy) reverberant data

RIR		Speaker identification rate (%)
Type	T₆₀ (ms)	Clean	Reverb.	Noisy reverberant
Type	T₆₀ (ms)	Clean	SNR = ∞	SNR = 20 dB	SNR = 10 dB
Office	400	98.0	74.3	55.3	20.6
Livingroom	400	98.0	70.9	-	-