水下噪声音色属性回归模型及其在目标识别中的应用

通过对声音的主观评价与客观分析而建立的主观感受数学模型,在许多领域都有重要的应用. 本文采用多元线性回归分析手段对水下噪声音色属性建立回归模型,提取音色特征并改善水下目标的识别效果. 首先,在前期水下噪声音色属性主观评价实验的基础上,将构成音色属性空间的5个成分的评价分值作为回归分析中的因变量,提取大量与听觉感知相关的听觉特征作为自变量;然后,通过相关分析和改进的逐步筛选法,挑选出反映音色属性的“最优”自变量子集;最后,利用向后剔除回归分析和水下目标识别实验,确定适当的音色模型,并通过假设检验证明该线性模型不仅正确有效,而且能改善水下目标识别效果. 关键词： 音色 多元线性回归 主观评价     

基于听觉中枢模型的水下噪声音色表达与特性分析

为建立水下噪声音色特征的定量表达以用于目标识别, 本文将主观评价实验获得的 4个本质音色维度得分与声音的听觉中枢响应建立联系, 得到音色的偏最小二乘回归模型, 并基于回归系数对每个维度进行物理分析. 为验证该方法的有效性, 本文提取大量音色描述符作为自变量进行对比, 结果表明听觉中枢模型预测能力有一定优势. 同时发现, 前 3个本质音色维度可分别由高频能量比例、谱平坦程度和时域连续性描述, 而第4 维度则无法与任何声学特征建立联系. 关键词： 本质音色 听觉中枢模型 偏最小二乘回归 音色描述符     

水下噪声听觉属性的主观评价与分析

为探求人耳感知水下目标类型的声学因素,研究了水下噪声听觉属性空间的维度数及其各维度的物理解释.首先通过词汇聚类分析和问卷调查确定评价水下噪声听觉属性的汉语描述词,然后完成基于成对比较法和语义细分法的主观评价实验,获得听觉属性的不相似性矩阵及各样本在不同听觉属性下的主观评价分值.最后,利用多维尺度分析确定水下噪声听觉属性空间由五个维度组成,再利用主成分分析得到独立的五个主成分,进而利用相关系数和压力值确定五个主成分分别表示听觉属性空间的五个维度,根据各个主成分对应的汉语描述词所反映的听觉属性对其进行物理解释 关键词： 听觉属性 多维尺度分析 主成分分析     

采用响应面回归的汽车多属性声品质预测方法*

单一主观评价分数无法准确描述人耳对声品质的多属性偏好特征。该文在多属性声品质试验数据的基础上,以愉悦度、平顺度和驾驶乐趣的主观评价分数为因变量,通过相关分析筛选出响度、尖锐度和A计权声压级3个主要自变量,引入响应面回归方法,分别建立因变量与自变量之间的预测模型,通过与多元线性模型和BP神经网络模型对比验证了精度。最后,建立多属性主观评价分数之间的量化映射模型。该研究可为多属性汽车声品质的优化控制提供参考。     

感知线性预测在水下目标分类中的应用研究

提出了基于感知线性预测(PLP)的模仿人耳听觉特性来提取水声信号鲁棒特征的方法。运用听觉心理学的三个概念: (1)临界带谱分析、(2)等响度曲线、(3)强度响度听觉幂率,形成估计听觉谱的方法,可获得一个12阶全极点模型的鲁棒特征矢量。运用这一特征矢量进行训练和识别的实验结果表明:(1)在不同的频率段内,人耳对6类目标辐射噪声信号敏感程度是不同的。(2)提取的基于听觉感知水下目标特征具有鲁棒性。(3)通过此方法提取的特征维数较低,运算速度快,识别的正确率比以往有所提高。     

水下无源声呐目标听觉域张量特征提取方法

特征提取是水下无源声呐目标分类识别的关键步骤,提出了一种基于听觉Patterson-Holdsworth耳蜗模型的听觉域张量特征提取方法。将耳蜗模型的滤波器冲激响应视为信号分解的基函数,根据听觉模型非线性尺度或常规线性尺度确定不同通道的中心频率,然后计算出相应通道的增益和带宽,并量化冲激响应的阶数和相位参数,得到信号分解基,再根据信号分解原理得到通道数×阶数×相位数的三阶张量特征,并通过计算测试样本张量特征与训练样本张量特征间的相似性实现了水下无源声呐目标的分类识别。海上实录无源声呐目标的分类识别实验表明,提取的张量特征具有比较好的分类识别性能,听觉模型等效矩形带宽尺度优于线性尺度划分中心频率,能够提高无源声呐的目标指示能力。      

汉语语境下的车辆噪声听觉属性评价与分析

研究了等响度车辆噪声听觉属性的空间维度及其汉语表述.首先通过问卷调查确定评价车辆噪声听觉属性的汉语描述词,然后完成基于成对比较法和语义细分法的主观评价实验,获得听觉属性的不相似度矩阵及描述词的等级顺序.最后,利用多维尺度分析和主成分分析法得到独立的用中文表达的车辆噪声听觉属性,结果表明:对于等响度的车辆噪声,其听觉属性可以用三个维度表示,分别用"粗糙"、"刺耳"和"起伏"描述.     

基于平板冲击声的声源特性表征及自动识别*

以平板结构导纳函数为纽带,建立冲击声信号特征与声源特性之间的关联,获得与声源属性密切相关的特征用于目标分类。针对四边简支矩形被击板,借助信号参数识别算法获得与声源物理属性有关的6维导纳特征,并从冲击声样本中提取80维音色特征,将音色特征和导纳特征做相关性分析,获得与声源物理属性相关的信号特征集。利用BP神经网络进行分类,结果表明,当采用与特定声源物理属性相关的信号特征子集时,分类效果达到同组最优。     

车辆噪声烦恼度的音色表达

烦恼度作为评价噪声对人影响的重要指标,受到广泛重视并获得应用。通过主观评价实验和数据统计分析,从音色角度对城市典型车辆噪声烦恼度进行建模并给予物理解释。研究发现:(1)车辆噪声烦恼度音色空间由四个维度构成;(2)利用多元线性回归方法给出的车辆噪声烦恼度模型与声样本烦恼度拟合较好;(3)烦恼度空间维度与特定频谱特性具有较高的相关性。研究结果为车辆噪声烦恼度建模及降噪设计提供了新的思路。      

水下激光目标的统计对消分割法

水下激光目标的识别是一个崭新的研究领域,有许多问题需要解决,其中,目标分割是关键.水下激光图像中夹杂着严重的散斑噪声,受其影响,要识别水下激光目标,就要对图像进行有效的消噪,然后进行目标分割.本文依据具有相似统计特征的噪声可抵消图像中的相应噪声这一基理,结合小波变换和统计法,提出了一种水下激光目标的统计对消分割法,以去除噪声,提取目标.实验结果表明该方法是有效可行的.     

Tensor feature extraction of underwater passive sonar target based on auditory model

Feature extraction is a key step for underwater passive sonar target classification and recognition.A kind of tensor feature extraction method based on auditory PattersonHoldsworth cochlear model is proposed.First,the filter impulse response of the cochlear model is regarded as the basis function of signal decomposition,and the center frequency of different channels is determined according to the nonlinear scale or conventional linear scale of the auditory model.Then,the gain and bandwidth of th...     

An auditory periphery model for improving narrow-band noise recognition rate of underwater targets

The recognition rate of the auditory periphery features decreases when the model is used to identify underwater targets in practice. To solve this problem, an improved method based on Gammatone filter bank is proposed. Firstly, after the reason of the decreasing of the recognition results is analyzed,the mechanism of multichannel data acquisition in acoustic engineering may narrow down signal frequency range, which leads to time-frequency features distortion. Secondly, the Gammatone filter bank is implemented to simulate frequency decomposition characteristics of human ear basilar membrane. Since the class information of the underwater noise signal is mostly contained in low frequency range, the auditory features of the conventional model are interpolated and the channel number of the filter bank and the central frequency of each frequency band are adjusted accordingly to obtain a 27-dimensional feature vector of the narrow-band target signal. The adjusted model may reflect the target's timefrequency feature more precisely. Finally, the performance of the auditory features is tested by a Neural Network classifier. The experiment results show that the modified auditory model is more effective than the conventional ones. The major information contained in broadband signals is reserved and the classification ability for real targets is further enhanced. The recognition results are increased from 82.59% to 88.80%. The modified auditory features effectively improve the recognition rate for underwater target radiated noise signals.     

Ambisonics声捡拾与重放音色的双耳听觉模型分析与实验

提出用双耳听觉模型对空间声音色进行分析的普遍方法,并以Ambisonics为例进行了分析。Ambisonics是基于物理声场重构的空间声系统,其最终重构声场误差以及音色改变是由传声器捡拾和重放空间混叠误差共同引起的。采用修正的Moore双耳响度模型计算了Ambisonics重构声场的双耳响度级谱并和目标声场的情况比较,从而定量评价重构声场的音色改变。结果表明,在理想捡拾信号的情况下,无音色改变重放的上限频率和区域大小随Ambisonics的阶数而增加。而对于传声器阵列捡拾的情况,只要阵列的上限频率大于Ambisonics重放的上限频率,在重放的上限频率以下,传声器阵列空间混叠误差对最终重构声场及其感知音色的影响就可以忽略。在此基础上,提出了一种综合考虑捡拾与重放性能的Ambisonics系统优化设计方法。心理声学实验得到了和双耳听觉模型一致的结果,从而也验证了模型分析的有效性。      

A perceptual space for underwater man-made sounds towards target classification

This work is the second part in a series of studies about the auditory features for underwater target classification, focusing on man-made vehicle targets (i.e. submarines, patrol boats and large surface ships). A psychoacoustic method, which is suitable for a small number of samples, was used. An optimal model with three common dimensions, specificities and latent classes was selected on the basis of the dissimilarity ratings among representative sounds and with the use of an extended version of the multidimensional scaling algorithm CLASCAL. However, such a three-dimensional space could not absolutely separate targets, whereas the first dimension in the four-dimensional space discriminated the submarines, patrol boats and ships; thus, the four-dimensional space was superior in target classification. The stepwise regression method was used to establish the relationships between individual dimensions and typical auditory features. Results showed that the first dimension was represented by the linear combination of zero-crossing rate and spectral variation, whereas the second dimension was described by attack slope. The last two dimensions were not associated with any features, and they were proved to include meaningless data noises. Finally, through a contrastive analysis, the perceptual space obtained in this study was found to be a good ‘local’ representation of the space in the first part of the study series.     

Analysis with binaural auditory model and experiment on the timbre of Ambisonics recording and reproduction

A scheme for analyzing the timbre in spatial sound with binaural auditory model is proposed and the Ambisonics is taken as an example for analysis.Ambisonics is a spatial sound system based on physical sound field reconstruction.The errors and timbre colorations in the final reconstructed sound field depend on the spatial aliasing errors on both the recording and reproducing stages of Ambisonics.The binaural loudness level spectra in Ambisonics reconstruction is calculated by using Moore's revised loudness model and then compared with the result of real sound source,so as to evaluate the timbre coloration in Ambisonics quantitatively.The results indicate that,in the case of ideal independent signals,the high-frequency limit and radius of region without perceived timbre coloration increase with the order of Ambisonics.On the other hand,in the case of recording by microphone array,once the high-frequency limit of microphone array exceeds that of sound field reconstruction,array recording influences little on the binaural loudness level spectra and thus timbre in final reconstruction up to the highfrequency limit of reproduction.Based on the binaural auditory model analysis,a scheme for optimizing design of Ambisonics recording and reproduction is also suggested.The subjective experiment yields consistent results with those of binaural model,thus verifies the effectiveness of the model analysis.     

The admittance feature representation and impact sound feature extraction in the material identification of ribbed plates

The admittance features representing the physical attributes are used as the intermediates to extract the material-attributes-related impact sound features of ribbed plates.Firstly, the admittance feature representations of metal ribbed plates attributes are obtained and the relationship between the admittance features and the impact sound features are established via correlation analysis method. Then, material-attributes-related impact sound features are obtained indirectly. Finally, the performances of different sound features for the material recognition of ribbed-metal plates are verified through the Support Vector Machine classifier.The results indicate that the obtained four sets of features can effectively identify the materials of the metal ribbed plates, while the accuracy of a single feature depends on the separable degree of the corresponding material attribute. And the features extracted based on admittance functions have higher average accuracy than that of timbre features. Therefore, the proposed sound feature extraction method based on admittance features is valid, and the extracted sound features can effectively reflect the physical attributes.