Published December 14, 2022
| Version v1
Conference paper
Open
Environment Classification via Blind Roomprints Estimation
-
1.
Fraunhofer Institute for Digital Media Technology
Description
In this paper we present a novel approach for environment classification for speech recordings, which does not require the selection of decaying reverberation tails. It is based on a multi-band RT60 analysis of blind channel estimates and achieves an accuracy of up to 93.8% on test recordings derived from the ACE corpus.
Files
baum_wifs22__environmentclassification.pdf
Files
(440.0 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:462fe7dd7b068cd791d496cfbf7266a8
|
440.0 kB | Preview Download |