无人机被动音频探测和识别技术研究

为解决近场空域低、慢、小旋翼无人机的安全威胁,提出基于音频信号分析的无人机探测识别方法。该方法采用改进流程和参数的梅尔频率倒谱系数(Mel-Frequency Cepstral Coeffi-cients,MFCC)和其一阶差分作为无人机音频的特征参数,结合提出的多距离分段采集法,通过训练高斯混合模型(Gaussian Mixture Model,GMM),建立多特征的无人机音频"指纹库",最后用特征匹配算法实现无人机的探测和识别。实验结果表明,所提出的方法在典型郊区环境中可实现150 m距离内无人机的探测和识别,识别率达到84.4%。     

A Phoneme-Based Approach for Eliminating Out-of-vocabulary Problem Turkish Speech Recognition Using Hidden Markov Model

Since Turkish is a morphologically productive language, it is almost impossible for a word-based recognition system to be realized to completely model Turkish language. Due to the fact that it is difficult for the system to recognize words not introduced to it in a word-based recognition system, recognition success rate drops considerably caused by out-of-vocabulary words. In this study, a speaker-dependent, phoneme-based word recognition system has been designed and implemented for Turkish Language to overcome the problem. An algorithm for finding phoneme-boundaries has been devised in order to segment the word into its phonemes. After the segmentation of words into phonemes, each phoneme is separated into different sub-groups according to its position and neighboring phonemes in that word. Generated sub-groups are represented by Hidden Markov Model, which is a statistical technique, using Mel-frequency cepstral coefficients as feature vector. Since phoneme-based approach is adopted in this study, it has been successfully achieved that many out of vocabulary words could be recognized.     

基于混合分布注意力机制与混合神经网络的语音情绪识别方法

针对现有语音情绪识别中存在无关特征多和准确率较差的问题,提出一种基于混合分布注意力机制与混合神经网络的语音情绪识别方法。该方法在2个通道内,分别使用卷积神经网络和双向长短时记忆网络进行语音的空间特征和时序特征提取,然后将2个网络的输出同时作为多头注意力机制的输入矩阵。同时,考虑到现有多头注意力机制存在的低秩分布问题,在注意力机制计算方式上进行改进,将低秩分布与2个神经网络的输出特征的相似性做混合分布叠加,再经过归一化操作后将所有子空间结果进行拼接,最后经过全连接层进行分类输出。实验结果表明,基于混合分布注意力机制与混合神经网络的语音情绪识别方法比现有其他方法的准确率更高,验证了所提方法的有效性。     

语音MFCC特征计算的改进算法

提出了一种计算Mel频倒谱参数(Mel frequency cepstral coefficient,MFCC)特征的改进算法,该算法采用了加权滤波器分析(Wrapped discrete Fourier transform,WDFT)技术来提高语音信号低频部分的频谱分辨率,使之更符合人类听觉系统的特性。同时还运用了加权滤波器分析(Weighted filter bank analysis,WFBA)技术,以提高MFCC的鲁棒性。对TIMIT连续语音数据库中DR1集的音素识别结果表明,本文提出的改进算法比传统MFCC算法具有更好的识别率。     

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%。     

Comparison of Khasi Speech Representations with Different Spectral Features and Hidden Markov States

In this paper, we present a comparison of Khasi speech representations with four different spectral features and novel extension towards the development of Khasi speech corpora. These four features include linear predictive coding (LPC), linear prediction cepstrum coefficient (LPCC), perceptual linear prediction (PLP), and Mel frequency cepstral coefficient (MFCC). The 10-hour speech data were used for training and 3-hour data for testing. For each spectral feature, different hidden Markov model (HMM) based recognizers with variations in HMM states and different Gaussian mixture models (GMMs) were built. The performance was evaluated by using the word error rate (WER). The experimental results show that MFCC provides a better representation for Khasi speech compared with the other three spectral features.     

特征空间本征音说话人自适应

提出了特征空间本征音说话人自适应算法,该方法首先借鉴RATZ 算法的思想,采用高斯混合模型对特征空间中的说话人信息进行建模;其次利用 子空间方法实现对特征补偿项的估计,减少估计参数的数量,在对特征空间精确建 模的同时,降低了算法对自适应数据量的需求.基于微软语料库的中文连续语 音识别实验表明,该算法在自适应数据量极少时仍能取得较好的性能,配合说话人自适 应训练能够进一步降低词错误率,其实时性优于本征音说话人自适应算法.     

Automatic speaker recognition from speech signal using bidirectional long-short-term memory recurrent neural network

Speaker recognition is a major challenge in various languages for researchers. For programmed speaker recognition structure prepared by utilizing ordinary speech, shouting creates a confusion between the enlistment and test, henceforth minimizing the identification execution as extreme vocal exertion is required during shouting. Speaker recognition requires more time for classification of data, accuracy is optimized, and the low root-mean-square error rate is the major problem. The objective of this work is to develop an efficient system of speaker recognition. In this work, an improved method of Wiener filter algorithm is applied for better noise reduction. To obtain the essential feature vector values, Mel-frequency cepstral coefficient feature extraction method is used on the noise-removed signals. Furthermore, input samples are created by using these extracted features after the dimensions have been reduced using probabilistic principal component analysis. Finally, recurrent neural network-bidirectional long-short-term memory is used for the classification to improve the prediction accuracy. For checking the effectiveness, the proposed work is compared with the existing methods based on accuracy, sensitivity, and error rate. The results obtained with the proposed method demonstrate an accuracy of 95.77%.     

基于DBN的液压泵劣化程度评估方法研究

针对轴向柱塞泵中心弹簧失效故障难以有效评估的问题,提出一种基于梅尔频率倒谱系数(MFCC)和深度信念神经网络(DBN)的液压泵劣化程度评估方法。对现场采集的正常数据和3种不同程度中心弹簧失效故障的液压泵振动信号进行信号预处理,包括预加重、分帧和加窗等;对预处理后的信号进行快速傅里叶变换(FFT),得到其频率谱和功率谱,然后让其通过Mel滤波器组,得到信号的对数能量;最后对对数能量进行离散余弦变换,得到信号的倒谱系数和一阶差分系数,并以此构成特征向量。基于DBN方法搭建深度学习模型,对特征向量进行学习,将测试样本导入深度学习模型,对中心弹簧失效程度进行评估,并将倒谱系数和一阶差分系数的识别结果进行对比。结果表明：当选择倒谱系数为特征向量时,具有较高的识别精度,能够有效识别轴向柱塞泵中心弹簧的性能劣化程度。     

一种改进的基于倒谱特征的带噪端点检测方法

影响语音识别性能的一个关键因素是端点检测的准确性。实际应用中的信噪比较低,使得某些高信噪比下性能好的检测算法不能有效地工作,影响系统的识别率。该文针对基于倒谱特征的带噪端点检测算法提出了3点改进：(1)将语音信号经滤波后分成高低频两子带,分别进行分析;(2)用LPC美尔倒谱特征LPCCMCC代替常规倒谱特征作为特征参数;(3)改进噪声估计,使其具有自适应性。实验结果表明本方法在低信噪比下有较好的检测性能。