Acoustic Denoising using Dictionary Learning with Spectral and Temporal Regularization.
Acoustic Denoising using Dictionary Learning with Spectral and Temporal Regularization.
复制标题
DOI：
10.1109/taslp.2018.2800280
复制
发表时间：
2018-05
期刊：
影响因子：
--
通讯作者：
Narayanan S
中科院分区：
文献类型：
--
作者：
Vaz C;Ramanarayanan V;Narayanan S
我们提出了一种语音增强的方法，收集在非常嘈杂的环境中，如磁共振成像（MRI）扫描过程中获得的数据。我们提出了一种基于字典学习的算法来执行这种增强。我们使用具有源内加性的复杂非负矩阵分解（CMF-WISA）来学习数据的噪声和语音+噪声部分的字典，并使用这些来将噪声频谱分解为估计的语音和噪声分量。我们增加CMF-WISA成本函数与频谱和时间正则化项，以改善噪声建模。基于客观和主观的评估，我们发现，我们的算法显着优于传统的技术，如最小均方（LMS）滤波，而不需要先验知识或特定的假设，如周期性的噪声波形，目前国家的最先进的算法需要。
We present a method for speech enhancement of data collected in extremely noisy environments, such as those obtained during magnetic resonance imaging (MRI) scans. We propose an algorithm based on dictionary learning to perform this enhancement. We use complex nonnegative matrix factorization with intra-source additivity (CMF-WISA) to learn dictionaries of the noise and speech+noise portions of the data and use these to factor the noisy spectrum into estimated speech and noise components. We augment the CMF-WISA cost function with spectral and temporal regularization terms to improve the noise modeling. Based on both objective and subjective assessments, we find that our algorithm significantly outperforms traditional techniques such as Least Mean Squares (LMS) filtering, while not requiring prior knowledge or specific assumptions such as periodicity of the noise waveforms that current state-of-the-art algorithms require.