Abstract
This paper presents a novel scheme for speech dereverberation. The core of our method is a two-stage single-channel speech enhancement scheme. Degraded speech obtains a sparser representation of the linear prediction residual in the first stage of our proposed scheme by applying orthogonal matching pursuit on overcomplete bases, trained by the K-SVD algorithm. Our method includes an estimation of reverberation and mixing time from a recorded hand clap or a simulated room impulse response, which are used to create a time-domain envelope. Late reverberation is suppressed at the second stage by estimating its energy from the previous envelope and removed with spectral subtraction. Further speech enhancement is applied on minimizing the background noise, based on optimal smoothing and minimum statistics. Experimental results indicate favorable quality, compared to two state-of-the-art methods, especially in real reverberant environments with increased reverberation and background noise.
Highlights
In many everyday places, the presence of reverb may undermine our listening experience
We compared the new method with the method of Wu and Wang [7] and the Spendred algorithm [8] for the two datasets
We presented a new method, based on the Wu and Wang algorithm [7], which can be considered an evolution of their method
Summary
The presence of reverb may undermine our listening experience. Depending on the surfaces’ sound absorbing properties, as well as the room’s dimensions, reverb’s effects can vary from pleasing to extremely annoying. The latter can occur in enclosed spaces that have not been explicitly designed for sound reproduction purposes. It might not always be possible to improve the room’s acoustics using sound-absorbing material and sound traps (e.g., historical buildings, churches) [1], as this may harm the room’s interiors In this case, we need to use signal processing algorithms to filter out the introduced reverb from the recordings. Additional speech degradation may occur during room recordings In these cases, the other usual suspects apart from reverberation are echo and background noise. The source of background noise may vary from simple air dissipation hiss inside the room to other sound sources outside the room (cars, rain, thunder, winds, etc.)
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call