基于SVM模型的自然环境声音的分类

提出了一种基于支持向量机（SVM）模型对自然环境声音进行分类的方法。首先,提取Mel频率倒谱系数（MFCCs）来分析声音信号;其次,对自然环境的声音基于MFCC特征集建立SVM模型;最后,使用交叉验证的测试方法得到基于SVM算法的分类结果。使用SVM模型对50类自然环境中的声音进行分类的正确率可达99.5704%,分类效果明显优于K最近邻（KNN）和二分嵌套整合（END）这两种算法。     

Local spectral variability features for speaker verification

Speaker verification techniques neglect the short-time variation in the feature space even though it contains speaker related attributes. We propose a simple method to capture and characterize this spectral variation through the eigenstructure of the sample covariance matrix. This covariance is computed using sliding window over spectral features. The newly formulated feature vectors representing local spectral variations are used with classical and state-of-the-art speaker recognition systems. Results on multiple speaker recognition evaluation corpora reveal that eigenvectors weighted with their normalized singular values are useful in representing local covariance information. We have also shown that local variability features can be extracted using mel frequency cepstral coefficients (MFCCs) as well as using three recently developed features: frequency domain linear prediction (FDLP), mean Hilbert envelope coefficients (MHECs) and power-normalized cepstral coefficients (PNCCs). Since information conveyed in the proposed feature is complementary to the standard short-term features, we apply different fusion techniques. We observe considerable relative improvements in speaker verification accuracy in combined mode on text-independent (NIST SRE) and text-dependent (RSR2015) speech corpora. We have obtained up to 12.28% relative improvement in speaker recognition accuracy on text-independent corpora. Conversely in experiments on text-dependent corpora, we have achieved up to 40% relative reduction in EER. To sum up, combining local covariance information with the traditional cepstral features holds promise as an additional speaker cue in both text-independent and text-dependent recognition.     

线性判别分析和支持向量机的音乐分类方法

提出了一种新的音乐分类方法,该方法使用线性判别分析(LDA)和支持向量机(SVMs)对音乐数据进行分类。在实现音乐分类中,先使用傅里叶变换等方法从每一段音乐中提取音频特征,包括Mel倒谱系数及基音频率等,并将它们按比例组成一个高维向量;再使用LDA对这些高维向量进行降维,使得各类音乐的类间离散度与类内离散度的比值最大;最后使用SVM等4种分类器对降维后的特征进行分类。实验证明LDA及SVM使得音乐分类的精确度有了较大的提高。     

Artificial neural networks as speech recognisers for dysarthric speech: Identifying the best-performing set of MFCC parameters and studying a speaker-independent approach

Dysarthria is a neurological impairment of controlling the motor speech articulators that compromises the speech signal. Automatic Speech Recognition (ASR) can be very helpful for speakers with dysarthria because the disabled persons are often physically incapacitated. Mel-Frequency Cepstral Coefficients (MFCCs) have been proven to be an appropriate representation of dysarthric speech, but the question of which MFCC-based feature set represents dysarthric acoustic features most effectively has not been answered. Moreover, most of the current dysarthric speech recognisers are either speaker-dependent (SD) or speaker-adaptive (SA), and they perform poorly in terms of generalisability as a speaker-independent (SI) model. First, by comparing the results of 28 dysarthric SD speech recognisers, this study identifies the best-performing set of MFCC parameters, which can represent dysarthric acoustic features to be used in Artificial Neural Network (ANN)-based ASR. Next, this paper studies the application of ANNs as a fixed-length isolated-word SI ASR for individuals who suffer from dysarthria. The results show that the speech recognisers trained by the conventional 12 coefficients MFCC features without the use of delta and acceleration features provided the best accuracy, and the proposed SI ASR recognised the speech of the unforeseen dysarthric evaluation subjects with word recognition rate of 68.38%.     

基于TMS320C6713的语音识别系统设计

通过选用德州仪器公司带浮点功能的TMS320C6713DSP芯片作为系统核心处理器,结合MSP430单片机作为外围控制器,给出了一种实时语音识别系统的设计方法。该系统核心算法采用美尔频率倒谱系数作为特征参数进行特征提取和动态时间规整(DTW)算法进行模式匹配。通过编程调试,该系统具有良好的灵活性和实时性,在抗噪声、鲁棒性和识别率等方面有明显的提高。该系统在许多领域可作为实用化的一种参考。     

基于改进MFCC融合特征及FA-PNN的驾驶员路怒情绪识别

现今关于驾驶员路怒情绪识别方法中语音特性分析相对较少,该研究以路怒情绪为研究对象,利用模拟驾驶系统建立数据集,通过分析驾驶员语音的频谱特征,将时域中短时能量及短时过零率特征参数和改进Mel频率倒谱系数（Mel frequency cepstral coefficients,MFCC）特征参数融合构成特征参数向量,利用萤火虫算法（firefly algorithm,FA）优化PNN神经网络（probabilistic neural networks）并构建识别模型,实现驾驶员路怒情绪的识别。实验结果表明,在相同神经网络下,改进MFCC融合特征提取方法相比传统MFCC特征提取方法具有更好的抗噪性。同时,FA-PNN模型的识别准确率为93.0%,相比传统PNN模型提高了11个百分点;F1-Score值为0.932 8,提高了0.104 7。该研究论证了语音信号处理技术对驾驶员路怒情绪识别的可行性,为汽车主动安全驾驶预警研究提供了新方法。     

噪声环境下基于能量检测的生态声音识别

无效声音段的存在导致噪声环境下声音识别方法的识别率迅速降低。为此,提出一种基于能量检测的抗噪声音识别方法。用能量检测方法检测背景噪声环境下的有用声音信号,对检测到的信号提取Mel频率倒谱系数特征,使用支持向量机对提取的特征向量训练分类模型,对含有噪声的生态环境声音进行识别。实验结果表明,该方法具有较好的抗噪能力,其在信噪比40 dB以下的识别率比添加能量检测前提高约25%。     

噪音情境下生态环境声音的分类

提出一种对含有噪音的生态环境声音进行分类的方法.首先,匹配追踪(Matching Pursuit,简称MP)算法可以提取有效信号的时-频特征,减弱噪音的干扰.支持向量机(support Vector Machine,简称SVM)分类器的鲁棒性比较好,所以提出使用SVM基于MP时-频特征建立模型(简称MP-SVM)对含有噪音的生态环境声音进行分类.实验得出MP-SVM可取得较好的分类效果,证明了MP时-频特征和SVM分类器具有较好的抗噪性.     

基于PDA平台的实时说话人识别系统

受到模型规模大和计算量大的限制,经典的基于高斯混合模型的说话人识别方法不适合于资源有限的PDA平台实时说话人自动识别要求。以Mel倒谱系数为说话人特征,运用主成分分类技术,结合定点数计算技术实现实时说话人自动识别。在19个用户的语音库上进行系统识别实验,此新型分类技术的训练时间缩短为基线系统的1/50,测试时间缩短为1/12,模型规模缩小为1/6,同时识别性能达到94.7%。     

基于LSTM神经网络的油浸式变压器异常声纹诊断方法研究

利用声音信号对电力变压器进行状态诊断是一种不停机、无接触的设备维护方法,可以诊断变压器异常状态类型。提出了一种基于LSTM神经网络的电力变压器异常诊断的方法,采集电力变压器在正常状态、过载和放电3种运行状态下发出的声音信号,将声音信号进行预处理并提取声音信号的MFCC特征,再将其通过一、二阶差分组合成一组声音特征的矢量,输入LSTM神经网络中进行训练。训练结果表明,将LSTM神经网络应用在电力变压器状态声音诊断上对3种状态的识别均能达到99%以上的准确率。