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 93.6% on test recordings derived from the ACE corpus.
翻译:在本文中,我们提出了一种新颖的语音录音环境分类方法,不需要选择衰变回动尾巴,它基于多波段RT60对盲道估计值的分析,根据ACE柱体的测试记录达到93.6%的准确度。