This paper presents a novel scheme for speech dereverberation. The core of our method\nis a two-stage single-channel speech enhancement scheme. Degraded speech obtains a sparser\nrepresentation of the linear prediction residual in the first stage of our proposed scheme by applying\northogonal matching pursuit on overcomplete bases, trained by the K-SVD algorithm. Our method\nincludes an estimation of reverberation and mixing time from a recorded hand clap or a simulated\nroom impulse response, which are used to create a time-domain envelope. Late reverberation is\nsuppressed at the second stage by estimating its energy from the previous envelope and removed with\nspectral subtraction. Further speech enhancement is applied on minimizing the background noise,\nbased on optimal smoothing and minimum statistics. Experimental results indicate favorable quality,\ncompared to two state-of-the-art methods, especially in real reverberant environments with increased\nreverberation and background noise.
Loading....