Emotion recognition from speech: a review

Emotion recognition from speech has emerged as an important research area in the recent past. In this regard, review of existing work on emotional speech processing is useful for carrying out further research. In this paper, the recent literature on speech emotion recognition has been presented considering the issues related to emotional speech corpora, different types of speech features and models used for recognition of emotions from speech. Thirty two representative speech databases are reviewed in this work from point of view of their language, number of speakers, number of emotions, and purpose of collection. The issues related to emotional speech databases used in emotional speech recognition are also briefly discussed. Literature on different features used in the task of emotion recognition from speech is presented. The importance of choosing different classification models has been discussed along with the review. The important issues to be considered for further emotion recognition research in general and in specific to the Indian context have been highlighted where ever necessary.     

Class-specific multiple classifiers scheme to recognize emotions from speech signals

Automatic emotion recognition from speech signals is one of the important research areas, which adds value to machine intelligence. Pitch, duration, energy and Mel-frequency cepstral coefficients (MFCC) are the widely used features in the field of speech emotion recognition. A single classifier or a combination of classifiers is used to recognize emotions from the input features. The present work investigates the performance of the features of Autoregressive (AR) parameters, which include gain and reflection coefficients, in addition to the traditional linear prediction coefficients (LPC), to recognize emotions from speech signals. The classification performance of the features of AR parameters is studied using discriminant, k-nearest neighbor (KNN), Gaussian mixture model (GMM), back propagation artificial neural network (ANN) and support vector machine (SVM) classifiers and we find that the features of reflection coefficients recognize emotions better than the LPC. To improve the emotion recognition accuracy, we propose a class-specific multiple classifiers scheme, which is designed by multiple parallel classifiers, each of which is optimized to a class. Each classifier for an emotional class is built by a feature identified from a pool of features and a classifier identified from a pool of classifiers that optimize the recognition of the particular emotion. The outputs of the classifiers are combined by a decision level fusion technique. The experimental results show that the proposed scheme improves the emotion recognition accuracy. Further improvement in recognition accuracy is obtained when the scheme is built by including MFCC features in the pool of features.     

语音情感识别研究综述

语音是人们传递信息内容的同时又表达情感态度的媒介,语音情感识别是人机交互的重要组成部分。由语音情感识别的概念和历史发展进程入手,从6个角度逐步展开对语音情感识别研究体系进行综述。分析常用的情感描述模型,归纳常用的情感语音数据库和不同类型数据库的特点,研究语音情感特征的提取技术。通过比对3种语音情感识别方法的众多学者的多方面研究,得出语音情感识别方法可期望应用场景的态势,展望语音情感识别技术的挑战和发展趋势。     

Context-Independent Multilingual Emotion Recognition from Speech Signals

This paper presents and discusses an analysis of multilingual emotion recognition from speech with database-specific emotional features. Recognition was performed on English, Slovenian, Spanish, and French InterFace emotional speech databases. The InterFace databases included several neutral speaking styles and six emotions: disgust, surprise, joy, fear, anger and sadness. Speech features for emotion recognition were determined in two steps. In the first step, low-level features were defined and in the second high-level features were calculated from low-level features. Low-level features are composed from pitch, derivative of pitch, energy, derivative of energy, and duration of speech segments. High-level features are statistical presentations of low-level features. Database-specific emotional features were selected from high-level features that contain the most information about emotions in speech. Speaker-dependent and monolingual emotion recognisers were defined, as well as multilingual recognisers. Emotion recognition was performed using artificial neural networks. The achieved recognition accuracy was highest for speaker-dependent emotion recognition, smaller for monolingual emotion recognition and smallest for multilingual recognition. The database-specific emotional features are most convenient for use in multilingual emotion recognition. Among speaker-dependent, monolingual, and multilingual emotion recognition, the difference between emotion recognition with all high-level features and emotion recognition with database-specific emotional features is smallest for multilingual emotion recognition—3.84%.     

Segment-based emotion recognition from continuous Mandarin Chinese speech

Recognition of emotion in speech has recently matured to one of the key disciplines in speech analysis serving next generation human-machine interaction and communication. However, compared to automatic speech recognition, that emotion recognition from an isolated word or a phrase is inappropriate for conversation. Because a complete emotional expression may stride across several sentences, and may fetch-up on any word in dialogue. In this paper, we present a segment-based emotion recognition approach to continuous Mandarin Chinese speech. In this proposed approach, the unit for recognition is not a phrase or a sentence but an emotional expression in dialogue. To that end, the following procedures are presented: First, we evaluate the performance of several classifiers in short sentence speech emotion recognition architectures. The results of the experiments show that the WD-KNN classifier achieves the best accuracy for the 5-class emotion recognition what among the five classification techniques. We then implemented a continuous Mandarin Chinese speech emotion recognition system with an emotion radar chart which is based on WD-KNN; this system can represent the intensity of each emotion component in speech. This proposed approach shows how emotions can be recognized by speech signals, and in turn how emotional states can be visualized.     

语音情感的维度特征提取与识别

研究了情绪的维度空间模型与语音声学特征之间的关系以及语音情感的自动识别方法。介绍了基本情绪的维度空间模型,提取了唤醒度和效价度对应的情感特征,采用全局统计特征减小文本差异对情感特征的影响。研究了生气、高兴、悲伤和平静等情感状态的识别,使用高斯混合模型进行4种基本情感的建模,通过实验设定了高斯混合模型的最佳混合度,从而较好地拟合了4种情感在特征空间中的概率分布。实验结果显示,选取的语音特征适合于基本情感类别的识别,高斯混合模型对情感的建模起到了较好的效果,并且验证了二维情绪空间中,效价维度上的情感特征对语音情感识别的重要作用。     

Emotion Recognition with Capsule Neural Network

For human-machine communication to be as effective as human-to-human communication, research on speech emotion recognition is essential. Among the models and the classifiers used to recognize emotions, neural networks appear to be promising due to the network’s ability to learn and the diversity in configuration. Following the convolutional neural network, a capsule neural network (CapsNet) with inputs and outputs that are not scalar quantities but vectors allows the network to determine the part-whole relationships that are specific 6 for an object. This paper performs speech emotion recognition based on CapsNet. The corpora for speech emotion recognition have been augmented by adding white noise and changing voices. The feature parameters of the recognition system input are mel spectrum images along with the characteristics of the sound source, vocal tract and prosody. For the German emotional corpus EMO-DB, the average accuracy score for 4 emotions, neutral, boredom, anger and happiness, is 99.69%. For Vietnamese emotional corpus BKEmo, this score is 94.23% for 4 emotions, neutral, sadness, anger and happiness. The accuracy score is highest when combining all the above feature parameters, and this score increases significantly when combining mel spectrum images with the features directly related to the fundamental frequency.     

Spoken emotion recognition using hierarchical classifiers

The recognition of the emotional state of speakers is a multi-disciplinary research area that has received great interest over the last years. One of the most important goals is to improve the voice-based human–machine interactions. Several works on this domain use the prosodic features or the spectrum characteristics of speech signal, with neural networks, Gaussian mixtures and other standard classifiers. Usually, there is no acoustic interpretation of types of errors in the results. In this paper, the spectral characteristics of emotional signals are used in order to group emotions based on acoustic rather than psychological considerations. Standard classifiers based on Gaussian Mixture Models, Hidden Markov Models and Multilayer Perceptron are tested. These classifiers have been evaluated with different configurations and input features, in order to design a new hierarchical method for emotion classification. The proposed multiple feature hierarchical method for seven emotions, based on spectral and prosodic information, improves the performance over the standard classifiers and the fixed features.     

Modular neural-SVM scheme for speech emotion recognition using ANOVA feature selection method

The speech signal consists of linguistic information and also paralinguistic one such as emotion. The modern automatic speech recognition systems have achieved high performance in neutral style speech recognition, but they cannot maintain their high recognition rate for spontaneous speech. So, emotion recognition is an important step toward emotional speech recognition. The accuracy of an emotion recognition system is dependent on different factors such as the type and number of emotional states and selected features, and also the type of classifier. In this paper, a modular neural-support vector machine (SVM) classifier is proposed, and its performance in emotion recognition is compared to Gaussian mixture model, multi-layer perceptron neural network, and C5.0-based classifiers. The most efficient features are also selected by using the analysis of variations method. It is noted that the proposed modular scheme is achieved through a comparative study of different features and characteristics of an individual emotional state with the aim of improving the recognition performance. Empirical results show that even by discarding 22% of features, the average emotion recognition accuracy can be improved by 2.2%. Also, the proposed modular neural-SVM classifier improves the recognition accuracy at least by 8% as compared to the simulated monolithic classifiers.     

Survey on speech emotion recognition: Features, classification schemes, and databases

Recently, increasing attention has been directed to the study of the emotional content of speech signals, and hence, many systems have been proposed to identify the emotional content of a spoken utterance. This paper is a survey of speech emotion classification addressing three important aspects of the design of a speech emotion recognition system. The first one is the choice of suitable features for speech representation. The second issue is the design of an appropriate classification scheme and the third issue is the proper preparation of an emotional speech database for evaluating system performance. Conclusions about the performance and limitations of current speech emotion recognition systems are discussed in the last section of this survey. This section also suggests possible ways of improving speech emotion recognition systems.     

自闭症干预中无监督自编码的语音情感识别

语音情感识别是人机交互中重要的研究内容,儿童自闭症干预治疗中的语音情感识别系统有助于自闭症儿童的康复,但是由于目前语音信号中的情感特征多而杂,特征提取本身就是一项具有挑战性的工作,这样不利于整个系统的识别性能.针对这一问题,提出了一种语音情感特征提取算法,利用无监督自编码网络自动学习语音信号中的情感特征,通过构建一个3层的自编码网络提取语音情感特征,把多层编码网络学习完的高层特征作为极限学习机分类器的输入进行分类,其识别率为84.14%,比传统的基于提取人为定义特征的识别方法有所提高.     

Cultural dependency analysis for understanding speech emotion

Speech has been one of the major communication medium for years and will continue to do so until video communication becomes widely available and easily accessible. Although numerous technologies have been developed to improve the effectiveness of speech communication system, human interaction with machines and robots are still far from ideal. It is acknowledged that human can communicate effectively with each other through the telephony system. This situation motivates many researchers to study in depth the human communication system, with emphasis on its ability to express and infer emotion for effective social communication. Understanding the interlocutors’ emotion and recognizing the listeners’ perception is the key to boost communication effectiveness and interaction. Nonetheless, the perceived emotion is subjective and very much dependent on culture, environment and the pre-emotional state of the listener. Attempts have been made to understand the influence of culture in speech emotion and researchers have reported mixed findings that lead us to believe there are some common acoustical characteristics that enable similar emotion to be discriminated universally across culture. Yet there are unique speech attributes that facilitate exclusive emotion recognition of a particular culture. Understanding culture dependency is thus important to the performance of the speech emotion recognition system.In this paper three different speech emotion databases; namely: Berlin Emo-db, NTU_American and NTU_Asian dataset were selected to represent three different cultures of European, American and Asian respectively focusing on three basic emotions of anger, happiness and sadness with neutral acting as a reference. Different data arrangements with accordance to varying degree of culture dependency were designed for the experimental setup to provide better understanding of inter-cultural and intra-cultural effect in recognizing the speech emotion. Features were extracted using Mel Frequency Cepstral Co-efficient (MFCC) method and classified with neural network (Multi Layer Perceptron (MLP)) and fuzzy neural networks; namely: Adaptive Network Fuzzy Inference System (ANFIS) and Generic Self-Organizing Fuzzy Neural Network (GenSOFNN) representing precise and linguistic fuzzy rule conjuncts respectively. From the experimental results, it can be observed that culture influences the speech emotion recognition accuracy. 75% accuracy performance was recorded for generalized homogeneous intra-cultural experiments whereas the accuracy performance dropped to almost as low as chance probability (25% for 4 classes) for both homogeneous and heterogeneous mixed-cultural inter-culture experiments. The two-stage culture-sensitive speech emotion recognition approach was subsequently proposed to discriminate culture and speech emotion. Results of the analysis show potential of using the proposed technique to recognize culture-influenced speech emotion, which can be extended in many applications, for instance call center and intelligent vehicle. Such analysis may help us to better understand the culture dependency of speech emotion and as a result the accuracy performance of the speech emotion recognition system can be boosted.     

A new hybrid PSO assisted biogeography-based optimization for emotion and stress recognition from speech signal

Speech signals and glottal signals convey speakers’ emotional state along with linguistic information. To recognize speakers’ emotions and respond to it expressively is very much important for human-machine interaction. To develop a subject independent speech emotion/stress recognition system, by identifying speaker's emotion from their voices, features from OpenSmile toolbox, higher order spectral features and feature selection algorithm, is proposed in this work. Feature selection plays an important role in overcoming the challenge of dimensionality in several applications. This paper proposes a new particle swarm optimization assisted Biogeography-based algorithm for feature selection. The simulations were conducted using Berlin Emotional Speech Database (BES), Surrey Audio-Visual Expressed Emotion Database (SAVEE), Speech under Simulated and Actual Stress (SUSAS) and also validated using eight benchmark datasets. These datasets are of different dimensions and classes. Totally eight different experiments were conducted and obtained the recognition rates in range of 90.31%–99.47% (BES database), 62.50%–78.44% (SAVEE database) and 85.83%–98.70% (SUSAS database). The obtained results convincingly prove the effectiveness of the proposed feature selection algorithm when compared to the previous works and other metaheuristic algorithms (BBO and PSO).     

Emotion recognition from speech using sub-syllabic and pitch synchronous spectral features

In this work, spectral features extracted from sub-syllabic regions and pitch synchronous analysis are proposed for speech emotion recognition. Linear prediction cepstral coefficients, mel frequency cepstral coefficients and the features extracted from high amplitude regions of spectrum are used to represent emotion specific spectral information. These features are extracted from consonant, vowel and transition regions of each syllable to study the contribution of these regions toward recognition of emotions. Consonant, vowel and the transition regions are determined using vowel onset points. Spectral features extracted from each pitch cycle, are also used to recognize emotions present in speech. The emotions used in this study are: anger, fear, happy, neutral and sad. The emotion recognition performance using sub-syllabic speech segments are compared with the results of conventional block processing approach, where entire speech signal is processed frame by frame. The proposed emotion specific features are evaluated using simulated emotion speech corpus, IITKGP-SESC (Indian Institute of Technology, KharaGPur-Simulated Emotion Speech Corpus). The emotion recognition results obtained using IITKGP-SESC are compared with the results of Berlin emotion speech corpus. Emotion recognition systems are developed using Gaussian mixture models and auto-associative neural networks. The purpose of this study is to explore sub-syllabic regions to identify the emotions embedded in a speech signal, and if possible, to avoid processing of entire speech signal for emotion recognition without serious compromise in the performance.     

面向语音情感识别的语谱特征提取算法研究

语音情感识别的精度很大程度上取决于不同情感间的特征差异性。从分析语音的时频特性入手,结合人类的听觉选择性注意机制,提出一种基于语谱特征的语音情感识别算法。算法首先模拟人耳的听觉选择性注意机制,对情感语谱信号进行时域和频域上的分割提取,从而形成语音情感显著图。然后,基于显著图,提出采用Hu不变矩特征、纹理特征和部分语谱特征作为情感识别的主要特征。最后,基于支持向量机算法对语音情感进行识别。在语音情感数据库上的识别实验显示,提出的算法具有较高的语音情感识别率和鲁棒性,尤其对于实用的烦躁情感的识别最为明显。此外,不同情感特征间的主向量分析显示,所选情感特征间的差异性大,实用性强。     

基于改进的排序式选举算法的语音情感融合识别

根据情感的连续空间模型,提出一种改进的排序式选举算法,实现多个情感分类器的融合,取得了很好的情感识别效果。首先以隐马尔可夫模型（HMM）和人工神经网络（ANN）为基础,设计了三种分类器;然后用改进的排序式选举算法,实现对三种分类器的融合。分别利用普通话情感语音库和德语情感语音库进行实验,结果表明,与几种传统融合算法相比,改进的排序式选举法能够取得更好的融合效果,其识别性能明显优于单分类器。该算法不仅简单,而且可移植性好,可用于其他任意多个情感分类器的融合。     

Employing both gender and emotion cues to enhance speaker identification performance in emotional talking environments

Speaker recognition performance in emotional talking environments is not as high as it is in neutral talking environments. This work focuses on proposing, implementing, and evaluating a new approach to enhance the performance in emotional talking environments. The new proposed approach is based on identifying the unknown speaker using both his/her gender and emotion cues. Both Hidden Markov Models (HMMs) and Suprasegmental Hidden Markov Models (SPHMMs) have been used as classifiers in this work. This approach has been tested on our collected emotional speech database which is composed of six emotions. The results of this work show that speaker identification performance based on using both gender and emotion cues is higher than that based on using gender cues only, emotion cues only, and neither gender nor emotion cues by 7.22 %, 4.45 %, and 19.56 %, respectively. This work also shows that the optimum speaker identification performance takes place when the classifiers are completely biased towards suprasegmental models and no impact of acoustic models in the emotional talking environments. The achieved average speaker identification performance based on the new proposed approach falls within 2.35 % of that obtained in subjective evaluation by human judges.     

Modelling speech emotion recognition using logistic regression and decision trees

Speech emotion recognition has been one of the interesting issues in speech processing over the last few decades. Modelling of the emotion recognition process serves to understand as well as assess the performance of the system. This paper compares two different models for speech emotion recognition using vocal tract features namely, the first four formants and their respective bandwidths. The first model is based on a decision tree and the second one employs logistic regression. Whereas the decision tree models are based on machine learning, regression models have a strong statistical basis. The logistic regression models and the decision tree models developed in this work for several cases of binary classifications were validated by speech emotion recognition experiments conducted on a Malayalam emotional speech database of 2800 speech files, collected from ten speakers. The models are not only simple, but also meaningful since they indicate the contribution of each predictor. The experimental results indicate that speech emotion recognition using formants and bandwidths was better modelled using decision trees, which gave higher emotion recognition accuracies compared to logistic regression. The highest accuracy obtained using decision tree was 93.63%, for the classification of positive valence emotional speech as surprised or happy, using seven features. When using logistic regression for the same binary classification, the highest accuracy obtained was 73%, with eight features.