Normal and hypoacoustic infant cry signal classification using time-frequency analysis and general regression neural network

Crying is the most noticeable behavior of infancy. Infant cry signals can be used to identify physical or psychological status of an infant. Recently, acoustic analysis of infant cry signal has shown promising results and it has been proven to be an excellent tool to investigate the pathological status of an infant. This paper proposes short-time Fourier transform (STFT) based time-frequency analysis of infant cry signals. Few statistical features are derived from the time-frequency plot of infant cry signals and used as features to quantify infant cry signals. General Regression Neural Network (GRNN) is employed as a classifier for discriminating infant cry signals. Two classes of infant cry signals are considered such as normal cry signals and pathological cry signals from deaf infants. To prove the reliability of the proposed features, two neural network models such as Multilayer Perceptron (MLP) and Time-Delay Neural Network (TDNN) trained by scaled conjugate gradient algorithm are also used as classifiers. The experimental results show that the GRNN classifier gives very promising classification accuracy compared to MLP and TDNN and the proposed method can effectively classify normal and pathological infant cries.     

A new variance-based approach for discriminative feature extraction in machine hearing classification using spectrogram features

Machine hearing is an emerging research field that is analogous to machine vision in that it aims to equip computers with the ability to hear and recognise a variety of sounds. It is a key enabler of natural human–computer speech interfacing, as well as in areas such as automated security surveillance, environmental monitoring, smart homes/buildings/cities. Recent advances in machine learning allow current systems to accurately recognise a diverse range of sounds under controlled conditions. However doing so in real-world noisy conditions remains a challenging task. Several front–end feature extraction methods have been used for machine hearing, employing speech recognition features like MFCC and PLP, as well as image-like features such as AIM and SIF. The best choice of feature is found to be dependent upon the noise environment and machine learning techniques used. Machine learning methods such as deep neural networks have been shown capable of inferring discriminative classification rules from less structured front–end features in related domains. In the machine hearing field, spectrogram image features have recently shown good performance for noise-corrupted classification using deep neural networks. However there are many methods of extracting features from spectrograms. This paper explores a novel data-driven feature extraction method that uses variance-based criteria to define spectral pooling of features from spectrograms. The proposed method, based on maximising the pooled spectral variance of foreground and background sound models, is shown to achieve very good performance for robust classification.     

Infant Cry Language Analysis and Recognition: An Experimental Approach

Recently, lots of research has been directed towards natural language processing. However, the baby's cry, which serves as the primary means of communication for infants, has not yet been extensively explored, because it is not a language that can be easily understood. Since cry signals carry information about a babies' wellbeing and can be understood by experienced parents and experts to an extent, recognition and analysis of an infant's cry is not only possible, but also has profound medical and societal applications. In this paper, we obtain and analyze audio features of infant cry signals in time and frequency domains. Based on the related features, we can classify given cry signals to specific cry meanings for cry language recognition. Features extracted from audio feature space include linear predictive coding (LPC), linear predictive cepstral coefficients (LPCC), Bark frequency cepstral coefficients (BFCC), and Mel frequency cepstral coefficients (MFCC). Compressed sensing technique was used for classification and practical data were used to design and verify the proposed approaches. Experiments show that the proposed infant cry recognition approaches offer accurate and promising results.      

Analysis and modeling of acoustic information for automatic dialect classification

A primary challenge in the field of automatic speech recognition is to understand and create acoustic models to represent individual differences in their spoken language. Individual’s age, gender; their speaking styles influenced by their dialect may be few of the reasons for these differences. This work investigates the dialectal differences by measuring the analysis of variance of acoustic features such as, formant frequencies, pitch, pitch slope, duration and intensity for vowel sounds. This paper attempts to discuss methods to capture dialect specific knowledge through vocal tract and prosody information extracted from speech that can be utilized for automatic identification of dialects. Kernel based support vector machine is utilized for measuring the dialect discriminating ability of acoustic features. For the spectral feature shifted delta cepstral coefficients along with Mel frequency cepstral coefficients gives a recognition performance of 66.97 %. Combination of prosodic features performs better with a classification score of 74 %. The model is further evaluated for the combination of spectral and prosodic feature set and achieves a classification accuracy of 88.77 %. The proposed model is compared with the human perception of dialects. The overall work is based on four dialects of Hindi; one of the world’s major languages.     

Multiclass support vector machines for environmental sounds classification in visual domain based on log-Gabor filters

This paper presents an approach aimed at recognizing environmental sounds for surveillance and security applications. We propose a robust environmental sound classification approach, based on spectrograms features derive from log-Gabor filters. This approach includes three methods. In the first two methods, the spectrograms are passed through an appropriate log-Gabor filter banks and the outputs are averaged and underwent an optimal feature selection procedure based on a mutual information criteria. The third method uses the same steps but applied only to three patches extracted from each spectrogram. To investigate the accuracy of the proposed methods, we conduct experiments using a large database containing 10 environmental sound classes. The classification results based on Multiclass Support Vector Machines show that the second method is the most efficient with an average classification accuracy of 89.62 %.     

Efficient feature combination techniques for emotional speech classification

The challenge to enhance the naturalness and efficiency of spoken language man–machine interface, emotional speech identification and its classification has been a predominant research area. The reliability and accuracy of such emotion identification greatly depends on the feature selection and extraction. In this paper, a combined feature selection technique has been proposed which uses the reduced features set artifact of vector quantizer (VQ) in a Radial Basis Function Neural Network (RBFNN) environment for classification. In the initial stage, Linear Prediction Coefficient (LPC) and time–frequency Hurst parameter (pH) are utilized to extract the relevant feature, both exhibiting complementary information from the emotional speech. Extensive simulations have been carried out using Berlin Database of Emotional Speech (EMO-DB) with various combination of feature set. The experimental results reveal 76 % accuracy for pH and 68 % for LPC using standalone feature set, whereas the combination of feature sets, (LP VQC and pH VQC) enhance the average accuracy level up to 90.55 %.     

An analysis of content-based classification of audio signals using a fuzzy c-means algorithm

Content-based audio signal classification into broad categories such as speech, music, or speech with noise is the first step before any further processing such as speech recognition, content-based indexing, or surveillance systems. In this paper, we propose an efficient content-based audio classification approach to classify audio signals into broad genres using a fuzzy c-means (FCM) algorithm. We analyze different characteristic features of audio signals in time, frequency, and coefficient domains and select the optimal feature vector by employing a noble analytical scoring method to each feature. We utilize an FCM-based classification scheme and apply it on the extracted normalized optimal feature vector to achieve an efficient classification result. Experimental results demonstrate that the proposed approach outperforms the existing state-of-the-art audio classification systems by more than 11% in classification performance.     

Improving performance of X-rated video classification with the optimized repeated curve-like spectrum feature and the skip-and-analysis processing

This paper addresses the automatic classification of X-rated videos by analyzing its obscene sounds. In this paper, we propose the optimized repeated curve-like spectrum feature for classifying obscene sounds and the skip-and-analysis processing for classifying videos. The optimized repeated curve-like spectrum feature uses the longer frame size for stationary frequency region based on the fact that most of obscene sounds, such as sexual moans and screams, consist of mostly vowels and the variation of syllables occurs slowly compared to general speech. It also uses the customized mel-scaled bandpass filter for the valid frequency regions of obscene sounds with the frequency contents mainly under 5 kHz. The skip-and-analysis processing is based on the video playback characteristics that a harmful or normal scene continues to be played at least for certain duration of time during a playback. When the skip-and-analysis processing is applied, clips to be analyzed are selected by skip interval values and only these selected clips are used to classify videos. The processing performances of the optimized repeated curve-like spectrum feature have improvements from 21 % to 25.6 % compared to the repeated curve-like spectrum feature without degradation of classification performance in clip-level classification. Furthermore, when the skip-and-analysis processing is applied, the processing performance of classifying is improved significantly by from 82.59 % to 95.03 % maintaining the classification performance of more than 90 % at F1-score.     

Deep features-based speech emotion recognition for smart affective services

Emotion recognition from speech signals is an interesting research with several applications like smart healthcare, autonomous voice response systems, assessing situational seriousness by caller affective state analysis in emergency centers, and other smart affective services. In this paper, we present a study of speech emotion recognition based on the features extracted from spectrograms using a deep convolutional neural network (CNN) with rectangular kernels. Typically, CNNs have square shaped kernels and pooling operators at various layers, which are suited for 2D image data. However, in case of spectrograms, the information is encoded in a slightly different manner. Time is represented along the x-axis and y-axis shows frequency of the speech signal, whereas, the amplitude is indicated by the intensity value in the spectrogram at a particular position. To analyze speech through spectrograms, we propose rectangular kernels of varying shapes and sizes, along with max pooling in rectangular neighborhoods, to extract discriminative features. The proposed scheme effectively learns discriminative features from speech spectrograms and performs better than many state-of-the-art techniques when evaluated its performance on Emo-DB and Korean speech dataset.

     

The speaker identification by using genetic wavelet adaptive network based fuzzy inference system

In this paper, an intelligent speaker identification system is presented for speaker identification by using speech/voice signal. This study includes both combination of the adaptive feature extraction and classification by using optimum wavelet entropy parameter values. These optimum wavelet entropy values are obtained from measured Turkish speech/voice signal waveforms using speech experimental set. It is developed a genetic wavelet adaptive network based on fuzzy inference system (GWANFIS) model in this study. This model consists of three layers which are genetic algorithm, wavelet and adaptive network based on fuzzy inference system (ANFIS). The genetic algorithm layer is used for selecting of the feature extraction method and obtaining the optimum wavelet entropy parameter values. In this study, one of the eight different feature extraction methods is selected by using genetic algorithm. Alternative feature extraction methods are wavelet decomposition, wavelet decomposition – short time Fourier transform, wavelet decomposition – Born–Jordan time–frequency representation, wavelet decomposition – Choi–Williams time–frequency representation, wavelet decomposition – Margenau–Hill time–frequency representation, wavelet decomposition – Wigner–Ville time–frequency representation, wavelet decomposition – Page time–frequency representation, wavelet decomposition – Zhao–Atlas–Marks time–frequency representation. The wavelet layer is used for optimum feature extraction in the time–frequency domain and is composed of wavelet decomposition and wavelet entropies. The ANFIS approach is used for evaluating to fitness function of the genetic algorithm and for classification speakers. It has been evaluated the performance of the developed system by using noisy Turkish speech/voice signals. The test results showed that this system is effective in detecting real speech signals. The correct classification rate is about 91% for speaker classification.     

A new optimum feature extraction and classification method for speaker recognition: GWPNN

Speech and speaker recognition is an important topic to be performed by a computer system. In this paper, an expert speaker recognition system based on optimum wavelet packet entropy is proposed for speaker recognition by using real speech/voice signal. This study contains both the combination of the new feature extraction and classification approach by using optimum wavelet packet entropy parameter values. These optimum wavelet packet entropy values are obtained from measured real English language speech/voice signal waveforms using speech experimental set. A genetic-wavelet packet-neural network (GWPNN) model is developed in this study. GWPNN includes three layers which are genetic algorithm, wavelet packet and multi-layer perception. The genetic algorithm layer of GWPNN is used for selecting the feature extraction method and obtaining the optimum wavelet entropy parameter values. In this study, one of the four different feature extraction methods is selected by using genetic algorithm. Alternative feature extraction methods are wavelet packet decomposition, wavelet packet decomposition – short-time Fourier transform, wavelet packet decomposition – Born–Jordan time–frequency representation, wavelet packet decomposition – Choi–Williams time–frequency representation. The wavelet packet layer is used for optimum feature extraction in the time–frequency domain and is composed of wavelet packet decomposition and wavelet packet entropies. The multi-layer perceptron of GWPNN, which is a feed-forward neural network, is used for evaluating the fitness function of the genetic algorithm and for classification speakers. The performance of the developed system has been evaluated by using noisy English speech/voice signals. The test results showed that this system was effective in detecting real speech signals. The correct classification rate was about 85% for speaker classification.     

基于发音特性的摩擦音和塞擦音分类算法

提出了一种基于发音特性的摩擦音和塞擦音分类方法,该方法首先基于Seneff听觉谱提取一组描述音段能量分布特性和谱统计量的特征参数,刻画两者在发音过程上的差异,然后采用支持向量机模型实现摩擦音和塞擦音的分类。实验结果表明,其干净语音分类准确率可以达到90.08%,信噪比为5dB的语音分类准确率可达到80.4%,与传统的基于时频能量分布特征的摩擦音和塞擦音分类方法相比,较大地提高了低信噪比下的性能。     

Low-complexity feature-mapped speech bandwidth extension

Today's telecommunications systems use a limited audio signal bandwidth. A typical bandwidth is 0.3-3.4 kHz, but recently it has been suggested that mobile phone networks will facilitate an audio signal bandwidth of 50 Hz-7 kHz. This is suggested since an increased bandwidth will increase the sound quality of the speech signals. Since only few telephones initially will have this facility, a method extending the conventional narrow frequency-band speech signal into a wide-band speech signal utilizing the receiving telephone only is suggested. This will give the impression of a wide-band speech signal. The proposed speech bandwidth extension method is based on models of speech acoustics and fundamentals of human hearing. The extension maps each speech feature separately. Care has been taken to deal with implementation aspects, such as noisy speech signals, speech signal delays, computational complexity, and processing memory usage.     

Adaptive network-based fuzzy inference system vs. other classification algorithms for warped LPC-based speech/music discrimination

Automatic discrimination of speech and music is an important tool in many multimedia applications. The paper presents an effective approach based on an adaptive network-based fuzzy inference system (ANFIS) for the classification stage required in a speech/music discrimination system. A new simple feature, called warped LPC-based spectral centroid (WLPC-SC), is also proposed. Comparison between WLPC-SC and the classical features proposed in the literature for audio classification is performed, aiming to assess the good discriminatory power of the proposed feature. The vector length used to describe the proposed psychoacoustic-based feature is reduced to a few statistical values (mean, variance and skewness). With the aim of increasing the classification accuracy percentage, the feature space is then transformed to a new feature space by LDA. The classification task is performed applying ANFIS to the features in the transformed space. To evaluate the performance of the ANFIS system for speech/music discrimination, comparison to other commonly used classifiers is reported. The classification results for different types of music and speech signals show the good discriminating power of the proposed approach.     

基于频谱空间域特征注意的音乐流派分类算法

为了提升深度卷积神经网络对音乐频谱流派特征的提取效果,提出一种基于频谱空间域特征注意的音乐流派分类算法模型DCNN-SSA。DCNN-SSA模型通过对不同音乐梅尔谱图的流派特征在空间域上进行有效标注,并且改变网络结构,从而在提升特征提取效果的同时确保模型的有效性,进而提升音乐流派分类的准确率。首先,将原始音频信号进行梅尔滤波,以模拟人耳的滤波操作对音乐的音强及节奏变化进行有效过滤,所生成的梅尔谱图进行切割后输入网络;然后,通过深化网络层数、改变卷积结构及增加空间注意力机制对模型在流派特征提取上进行增强;最后,通过在数据集上进行多批次的训练与验证来有效提取并学习音乐流派特征,从而得到可以对音乐流派进行有效分类的模型。在GTZAN数据集上的实验结果表明,基于空间注意的音乐流派分类算法与其他深度学习模型相比,在音乐流派分类准确率和模型收敛效果上有所提高,准确率提升了5.36个百分点～10.44个百分点。     

Improvement to speech-music discrimination using sinusoidal model based features

This paper addresses a model-based audio content analysis for classification of speech-music mixed audio signals into speech and music. A set of new features is presented and evaluated based on sinusoidal modeling of audio signals. The new feature set, including variance of the birth frequencies and duration of the longest frequency track in sinusoidal model, as a measure of the harmony and signal continuity, is introduced and discussed in detail. These features are used and compared to typical features as inputs to an audio classifier. Performance of these sinusoidal model features is evaluated through classification of audio into speech and music using both the GMM (Gaussian Mixture Model) and the SVM (Support Vector Machine) classifiers. Experimental results show that the proposed features are quite successful in speech/music discrimination. By using only a set of two sinusoidal model features, extracted from 1-s segments of the signal, we achieved 96.84% accuracy in the audio classification. Experimental comparisons also confirm superiority of the sinusoidal model features to the popular time domain and frequency domain features in audio classification.     

基于卷积神经网络的翻录语音检测算法

针对翻录语音攻击说话人识别系统,危害合法用户的权益问题,提出了一种基于卷积神经网络（CNN）的翻录语音检测算法。首先,通过提取原始语音与翻录语音的语谱图,并将其输入到卷积神经网络中,对其进行特征提取及分类;然后,搭建了适应于检测翻录语音的网络框架,分析讨论了输入不同窗移的语谱图对检测率的影响;最后,对不同偷录及回放设备的翻录语音进行了交叉实验检测,并与现有的经典算法进行了对比。实验结果表明,所提方法能够准确地判断待测语音是否为翻录语音,其识别率达到了99.26%,与静音段梅尔频率倒谱系数（MFCC）算法、信道模式噪声算法和长时窗比例因子算法相比,识别率分别提高了约26个百分点、21个百分点和0.35个百分点。     

类独立特征提取法在环境声音识别中的应用

语音和非语音类声音的识别在很多系统的研发中都有非常重要的作用,如安全监控、医疗保健、现代化的视听会议系统等。虽然绝大多数声音信号都有其独特的发音机制,然而要从其中进行特征的提取往往缺乏系统有效的方法。基于不同的音频信号都有其固有的特点,使用类所属特征选择方法来提取音频中的特征,从而进行分类,并用所提出的方法对语音和两种非语音类声音（咳嗽和杯碟破碎的声音）进行了实验仿真,实验结果表明,与常规的特征选择方法相比,提出的方法用更少的特征实现了更好的分类。     

Heart sound classification based on scaled spectrogram and tensor decomposition

Heart sound signal analysis is an effective and convenient method for the preliminary diagnosis of heart disease. However, automatic heart sound classification is still a challenging problem which mainly reflected in heart sound segmentation and feature extraction from the corresponding segmentation results. In order to extract more discriminative features for heart sound classification, a scaled spectrogram and tensor decomposition based method was proposed in this study. In the proposed method, the spectrograms of the detected heart cycles are first scaled to a fixed size. Then a dimension reduction process of the scaled spectrograms is performed to extract the most discriminative features. During the dimension reduction process, the intrinsic structure of the scaled spectrograms, which contains important physiological and pathological information of the heart sound signals, is extracted using tensor decomposition method. As a result, the extracted features are more discriminative. Finally, the classification task is completed by support vector machine (SVM). Moreover, the proposed method is evaluated on three public datasets offered by the PASCAL classifying heart sounds challenge and 2016 PhysioNet challenge. The results show that the proposed method is competitive.     

Emotion modeling from speech signal based on wavelet packet transform

The recognition of emotion in human speech has gained increasing attention in recent years due to the wide variety of applications that benefit from such technology. Detecting emotion from speech can be viewed as a classification task. It consists of assigning, out of a fixed set, an emotion category e.g. happiness, anger, to a speech utterance. In this paper, we have tackled two emotions namely happiness and anger. The parameters extracted from speech signal depend on speaker, spoken word as well as emotion. To detect the emotion, we have kept the spoken utterance and the speaker constant and only the emotion is changed. Different features are extracted to identify the parameters responsible for emotion. Wavelet packet transform (WPT) is found to be emotion specific. We have performed the experiments using three methods. Method uses WPT and compares the number of coefficients greater than threshold in different bands. Second method uses energy ratios of different bands using WPT and compares the energy ratios in different bands. The third method is a conventional method using MFCC. The results obtained using WPT for angry, happy and neutral mode are 85 %, 65 % and 80 % respectively as compared to results obtained using MFCC i.e. 75 %, 45 % and 60 % respectively for the three emotions. Based on WPT features a model is proposed for emotion conversion namely neutral to angry and neutral to happy emotion.