Sri Sathya Sai Institute of Higher Learning, Prasanthi Nilayam AP 515134, India.
J Acoust Soc Am. 2012 Oct;132(4):EL329-35. doi: 10.1121/1.4751987.
Codebook-based speech enhancement methods that use trained codebooks of speech and noise spectra provide good performance even under non-stationary noise conditions. A drawback, however, is their high computational cost. For every pair of speech and noise codebook vectors, a likelihood score indicating how well that pair matches the observation is computed. In this paper, a method that identifies and performs only relevant likelihood computations by imposing a hierarchical structure on the speech codebook is proposed. The performance of the proposed method is shown to be close to that of the original scheme but at a significantly lower computational cost.
基于码本的语音增强方法使用经过训练的语音和噪声谱码本来提供良好的性能，即使在非平稳噪声条件下也是如此。然而，其缺点是计算成本高。对于每一对语音和噪声码本向量，都会计算一个似然分数，指示该对向量与观察结果的匹配程度。本文提出了一种通过在语音码本上施加层次结构来识别和仅执行相关似然计算的方法。所提出的方法的性能被证明接近于原始方案，但计算成本显著降低。
