Skip to main content
EURASIP Journal on Audio, Speech, and Music Processing

Table 4 Conditions for GSS-based dereverberation

From: Distant-talking speaker identification by generalized spectral subtraction-based dereverberation and its efficient computation

Analysis window

Hamming

Window length

32 ms

Window shift

16 ms

Number of reverberant windows D

6

 

(192 ms)

Spectral floor parameter β

0.15

Back to article page