Evaluation of spectral subtraction with smoothing of time direction on the Aurora 2 task
Evaluation of spectral subtraction with smoothing of time direction on the Aurora 2 task
复制标题
在 Aurora 2 任务上评估具有时间方向平滑的光谱减法
DOI：
10.21437/icslp.2002-23
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
S. Nakagawa
中科院分区：
文献类型：
--
作者：
N. Kitaoka;S. Nakagawa
为了减小加性噪声的影响，通常采用谱减法（SS）。我们在功率谱域上讨论SS。该方法存在两方面的问题，给纯净语音的估计带来困难：(1)噪声的真实功率谱与估计功率谱之间存在估计误差；(2)由于相位差的存在，语音与噪声之间存在相关性。为了克服这些问题，我们提出了一种基于时间方向平滑的谱减法。我们将估计的语音功率谱在一些帧上的平均值作为估计的语音功率谱。该操作使噪声的估计更加准确。我们可以降低语音和噪声之间相关性的影响。在本文中，我们在aurora 2数据库中对该方法进行了测试，该数据库由英文连接数字和各种真实噪声组成。在清洁条件下训练的声学模型的单词准确率相对提高了47.26%，在多条件下训练的声学模型的准确率相对提高了11.95%。
To reduce the effects of additive noises, spectral subtraction (SS) is often used. We discuss SS on the power spectral domain. This method has two problems to make the estimation of clean speech difficult:(1) There exists the estimation error between true power spectrum of noise and estimated one (2) The correlation between speech and noise also exists because of the phase difference. To overcome these problems, we proposed a spectral subtraction using a smoothing method of time direction. We consider the average of estimated speech power spectra over some frames as the estimated speech power spectrum. This operation makes the estimation of noise more accurate. We can reduce the effect of correlation between speech and noise. In this paper, we testedthis methodon theAURORA 2database, which consists of English connected digit added with various realistic noises. We achieved 47.26% relative improvement of word accuracy with acoustic models trained under clean condition and 11.95% with models trained under multi-condition.