水下目标回声特征提取是主动目标识别的关键内容。本文提出将语音识别领域中较为成熟的RASTA-PLP听觉模型应用于水中目标回波的特征提取，并根据信号的特点对RASTA-PLP模型进行修正。对比应用PLP方法进行的水中目标单频回波识别实验，结果表明：当加入卷积噪声后，修正的RASTA-PLP特征表现出更加良好的鲁棒性能，在同等测试条件下识别率比PLP听觉模型特征高约3%，显示了本方法在实现目标回声自动识别上的重要应用前景。
The more mature RASTA-PLP auditory mode in the field of speech recognition is presented to apply to the field of underwater target echo recognition. But also, According to the character of underwater target signal, The RASTA-PLP auditory mode is modified. Contrast to the PLP auditory model feature, the modified RASTA-PLP auditory model feature is more robust to underwater target echo signal after the Gauss white noise is convoluted with the signal. At the equal test condition, the recognition ratio of the modified RASTA-PLP auditory model feature is 3% higher than the PLP auditory model feature. It shows the method important foreground in underwater target recognition.
2016,38(12): 143-146,177 收稿日期：2016-07-12
DOI：10.3404/j.issn.1672-7619.2016.12.029
分类号：TN911.7
作者简介：吴亮(1980-),男,工程师,研究方向为舰船监造及水声电子工程。
参考文献：
[1] HERMANSKY H. Perceptual linear predictive (PLP) analysis of speech[J]. The Journal of the Acoustical Society of America, 1990, 87(4):1738-1752.
[2] HERMANSKY H, MORGAN N, BAYYA A, et al. RASTA-PLP speech analysis technique[C]//Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. San Francisco, CA:IEEE, 1992, 1:121-124.
[3] HERMANSKY H, MORGAN N. RASTA processing of speech[J]. IEEE Transactions on Speech and Audio Processing, 1994, 2(4):578-589.
[4] ZWICKER E, FASTL H. Psychoacoustics:Facts and models[M]. New York:Springer-Verlag, 1999.
[5] GHITZA O. Auditory models and human performance in tasks related to speech coding and speech recognition[J]. IEEE Transactions on Speech and Audio Processing, 1994, 2(1):115-132.
[6] USAGAWA T, IWATA M, EBATA M. Speech parameter extraction in noisy environment using a masking model[C]//Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing. Adelaide, SA:IEEE, 1994, 2:Ⅱ/81-Ⅱ/84.
[7] DUZENLI O. Classification of underwater signals using wavelet-based decompositions[D]. California:Naval Postgraduate School, 1998.
[8] CHERKASSKY V, MULIER F. Guest editorial vapnik-chervonenkis (VC) learning theory and its applications[J]. IEEE Transactions on Neural Networks, 1999, 10(5):985-987.
[9] 彭圆, 王晟, 王科俊, 等. 感知线性预测在水下目标分类中的应用研究[J]. 声学学报, 2006, 31(2):146-150. PENG Yuan, WANG Sheng, WANG Jun-ke, et al. A study on underwater target classification applying perception linear prediction method[J]. Acta Acustica, 2006, 31(2):146-150.
