Adapting Multiple Distributions for Bridging Emotions from Different Speech Corpora

The acoustic cues that convey emotion in speech are similar to those that convey emotion in music, and recognition of emotion in both of these types of cue recruits overlapping networks in the brain. Given the similarities between music and speech prosody, developmental research is uniquely positioned to determine whether recognition of these cues develops in parallel. In the present study, we asked 60 children aged 6 to 11 years, and 51 university students, to judge the emotions of 10 musical excerpts, 10 inflected speech clips, and 10 affect burst clips. We presented stimuli intended to convey happiness, sadness, anger, fear, and pride. Each emotion was presented twice per type of stimulus. We found that recognition of emotions in music and speech developed in parallel, and adult-levels of recognition develop later for these stimuli than for affect bursts. We also found that sad stimuli were most easily recognised, followed by happiness, fear, and then anger. In addition, we found that recognition of emotion in speech and affect bursts can predict emotion recognition in music stimuli independently of age and musical training. Finally, although proud speech and affect bursts were not well recognised, children aged eight years and older showed adult-like responses in recognition of proud music.

Speech emotion recognition (SER) is important in enabling personalized services and multimedia applications in our life. It also becomes a prevalent topic of research with its potential in creating a better user experience across many modern technologies. However, the highly contextualized scenario and expensive emotion labeling required cause a severe mismatch between already limited-in-scale speech emotional corpora; this hinders the wide adoption of SER. In this work, instead of conventionally learning a common feature space between corpora, we take a novel approach in enhancing the variability of the source (labeled) corpus that is target (unlabeled) data-aware by generating synthetic source domain data using a conditional cycle emotion generative adversarial network (CCEmoGAN). Note that no target samples with label are used during whole training process. We evaluate our framework in cross corpus emotion recognition tasks and obtain a three classes valence recognition accuracy of 47.56%, 50.11% and activation accuracy of 51.13%, 65.7% when transferring from the IEMOCAP to the CIT dataset, and the IEMOCAP to the MSP-IMPROV dataset respectively. The benefit of increasing target domain-aware variability in the source domain to improve emotion discriminability in cross corpus emotion recognition is further visualized in our augmented data space.

In the field of speech emotion recognition(SER), great progress has been made in feature extraction and classifier construction. However, in the natural environment, speech emotion recognition is vulnerable to environmental noise. Moreover, cross-corpus SER is a thorny problem because the gender differences and language differences between corpus. Therefore, these problems need to be solved. Considering the noise problem, wavelet threshold denoising was proposed. After that, this paper used multi-task learning method to solve the problem of languages and gender differences. Emotion recognition is primary task, while gender recognition and language recognition are auxiliary tasks. According to the multi-task learning model, the shared LSTM is designed to extract the shared features. Three private LSTMs are used to extract the features of emotion recognition ,language recognition and gender recognition respectively. Orthogonal constraint training was used to make the private space contain only private features. Two experiments are designed in this paper. The first experiment is the comparison between different wavelet bases and different numbers of decomposition layers to select suitable wavelet base and the number of decomposition layer. The second experiment is the comparison between cross-corpus SER in other literature.

Emotions are an integral part of social interactions, serving vital functions in the management of our interpersonal relationships. Cues to emotional meaning can be conveyed through a variety of modalities, from facial expressions and body gestures to the linguistic and non-linguistic, or prosodic aspects of speech. As automatic speech systems continue to grow in use, the ability to recognize emotional cues from these modalities is no longer solely expected in human communication, but also in human-computer interactions with the goal of developing more user-friendly and effective applications. This thesis explores how speech emotion recognition (SER) systems can be more robust to factors of language, culture, and context through the lens of emotional speech and emotional prosody from bilingual English-speaking Singaporeans of Chinese, Malay, or Indian ethnicity. Specifically, the thesis aims to examine how Singaporeans from the three ethnic groups may vary in their perception of emotions in speech, and to explore how they express emotions via speech prosody. The recognition and production processes of emotional communication in Singapore English was investigated through two emotion classes – anger and happiness. An emotion perception test was conducted using acted angry and happy speech as stimuli to understand how Singapore English speakers recognized emotions in speech. The results of the perception test revealed that respondents displayed very similar patterns in their rating of emotional speech stimuli. The study also found that respondents tended to rated anger with low dominance. At the same time, a spontaneous speech corpus known as the Singapore English Spontaneous Emotional Speech Corpus (SESESC) was also developed, featuring audio recordings of 44 Singapore English speakers from the three ethnic groups playing a co-operative video game with either a familiar partner or a confederate. More than 36,000 intervals were annotated in-context of the recordings by each annotator based on a modified emotion annotation scheme that included information regarding the emotion category and arousal levels. Intervals that were labelled as conveying joy or anger with full agreement from the annotators were selected following a series of criteria to facilitate comparable prosodic analyses given the inherent dynamicity of spontaneous speech. The analysis focused on exploring the F0 movements of the selected utterances in tandem with periodic energy. Overall, it was observed that utterances conveying happiness were associated more with level contours, while angry utterances were produced with more steep falling contours especially on the utterance-final syllable. A tendency for an F0 peak to be produced on the second syllable of the utterance was also observed in both sets of data analyzed, alluding to the interactions between emotional prosody and the intonational structure of Singapore English. Finally, an emotion classification was conducted using a subset of the corpus as test data for a fine-tuned SER model. Results showed that while utterances conveying happiness could be automatically recognized to a high percentage of 86%, there was also a high percentage of misclassification of anger. This result appears to counter findings in past SER studies, which typically reported high levels of recognition accuracy for anger. Taken together, the thesis contributes an understanding of how spontaneous speech and emotional cues on the prosodic level interact even in task-oriented conversations, with further considerations of how these patterns may vary among bilinguals in multicultural contexts, so as to enable more robust speech emotion recognition systems in the future.

Purpose of research.Emotions play one of the key roles in the regulation of human behaviour. Solving the problem of automatic recognition of emotions makes it possible to increase the effectiveness of operation of a whole range of digital systems such as security systems, human-machine interfaces, e-commerce systems, etc. At the same time, the low efficiency of modern approaches to recognizing emotions in speech can be noted. This work studies automatic recognition of emotions in speech applying machine learning methods.Methods.The article describes and tests an approach to automatic recognition of emotions in speech based on multitask learning of deep convolution neural networks of AlexNet and VGG architectures using automatic selection of the weight coefficients for each task when calculating the final loss value during learning. All the models were trained on a sample of the IEMOCAP dataset with four emotional categories of ‘anger’, ‘happiness’, ‘neutral emotion’, ‘sadness’. The log-mel spectrograms of statements processed by a specialized algorithm are used as input data.Results.The considered models were tested on the basis of numerical metrics: the share of correctly recognized instances, accuracy, completeness, f-measure. For all of the above metrics, an improvement in the quality of emotion recognition by the proposed model was obtained in comparison with the two basic single-task models as well as with known solutions. This result is achieved through the use of automatic weighting of the values of the loss functions from individual tasks when forming the final value of the error in the learning process.Conclusion.The resulting improvement in the quality of emotion recognition in comparison with the known solutions confirms the feasibility of applying multitask learning to increase the accuracy of emotion recognition models. The developed approach makes it possible to achieve a uniform and simultaneous reduction of errors of individual tasks, and is used in the field of emotions recognition in speech for the first time.

Self-labeling with feature transfer for speech emotion recognition

Subject matter: Speech emotion recognition (SER) is an ongoing interesting research topic. Its purpose is to establish interactions between humans and computers through speech and emotion. To recognize speech emotions, five deep learning models: Convolution Neural Network, Long-Short Term Memory, Artificial Neural Network, Multi-Layer Perceptron, Merged CNN, and LSTM Network (CNN-LSTM) are used in this paper. The Toronto Emotional Speech Set (TESS), Surrey Audio-Visual Expressed Emotion (SAVEE) and Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) datasets were used for this system. They were trained by merging 3 ways TESS+SAVEE, TESS+RAVDESS, and TESS+SAVEE+RAVDESS. These datasets are numerous audios spoken by both male and female speakers of the English language. This paper classifies seven emotions (sadness, happiness, anger, fear, disgust, neutral, and surprise) that is a challenge to identify seven emotions for both male and female data. Whereas most have worked with male-only or female-only speech and both male-female datasets have found low accuracy in emotion detection tasks. Features need to be extracted by a feature extraction technique to train a deep-learning model on audio data. Mel Frequency Cepstral Coefficients (MFCCs) extract all the necessary features from the audio data for speech emotion classification. After training five models with three datasets, the best accuracy of 84.35 % is achieved by CNN-LSTM with the TESS+SAVEE dataset.

To solve the problem of feature distribution discrepancy in cross-corpus speech emotion recognition tasks, this paper proposed an emotion recognition model based on multi-task learning and subdomain adaptation, which alleviates the impact on emotion recognition. Existing methods have shortcomings in speech feature representation and cross-corpus feature distribution alignment. The proposed model uses a deep denoising auto-encoder as a shared feature extraction network for multi-task learning, and the fully connected layer and softmax layer are added before each recognition task as task-specific layers. Subsequently, the subdomain adaptation algorithm of emotion and gender features is added to the shared network to obtain the shared emotion features and gender features of the source domain and target domain, respectively. Multi-task learning effectively enhances the representation ability of features, a subdomain adaptive algorithm promotes the migrating ability of features and effectively alleviates the impact of feature distribution differences in emotional features. The average results of six cross-corpus speech emotion recognition experiments show that, compared with other models, the weighted average recall rate is increased by 1.89~10.07%, the experimental results verify the validity of the proposed model.

-- Speech signals are being considered as most effective means of communication between human beings. Many researchers have found different methods or systems to identify emotions from speech signals. Here, the various features of speech are used to classify emotions. Features like pitch, tone, intensity are essential for classification. Large number of the datasets are available for speech emotion recognition. Firstly, the extraction of features from speech emotion is carried out and then another important part is classification of emotions based upon speech. Hence, different classifiers are used to classify emotions such as Happy, Sad, Anger, Surprise, Neutral, etc. Although, there are other approaches based on machine learning algorithms for identifying emotions. Speech Emotion Recognition is a current research topic because of its wide range of applications and it became a challenge in the field of speech processing too. We have carried out a brief study on Speech Emotion Analysis along with Emotion Recognition. Speech Emotion Recognition (SER) can be defined as extraction of the emotional state of the speaker from his or her speech signal. There are few universal emotions including Neutral, Anger, we have worked on different tools to be used in SER. SER is tough because emotions are subjective and annotating audio is challenging task. Emotion recognition is the part of speech recognition which is gaining more popularity and need for it increases enormously. We have classified based on different type of emotions to detect from speech. Key Words: Speech Emotion Recognition, Affective Computing, Machine Learning, Deep Learning, Audio Signal Processing, Emotion Classification, Feature Extraction, Prosodic Features, Spectral Features, Mel-Frequency Cepstral Coefficients (MFCCs), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Attention Mechanisms, Multimodal Emotion Recognition, Speaker-Independent SER, Real-Time Emotion Detection, Noise-Robust Emotion Recognition, Data Augmentation, Emotion-Aware Applications

Emotions are important for human well-being and social connections. This work focuses on the issue of effectively understanding emotions in human speech, specifically in the context of Industry 5.0. Traditional approaches and machine learning (ML) techniques for identifying emotions in speech are limited, such as the requirement for complicated feature extraction. Traditional methods yield recognition accuracies of no more than 90% because to the restricted extraction of temporal/sequence information. This paper suggests a ground-breaking fusion-based deep learning (DL) method to overcome these limitations. Specifically, one-dimensional (1D) and two-dimensional (2D) convolution neural network (CNN) can automatically extract significant characteristics and handle enormous datasets in real time. Furthermore, a fusion-based DL network, speech emotion recognition deep learning fusion network (SER_DLFNet), has been proposed, which combines CNN with long short-term memory (LSTM) to collect sequence information and increase recognition accuracy. The proposed model shows impressive results, with a test accuracy of 95.52% on the ryerson audio-visual database of emotional speech and song (RAVDESS) dataset. This research contributes to the advancement of more precise and efficient emotion identification algorithms for voice analysis, especially within the framework of Industry 5.0.

Speech emotion recognition (SER) is an important field of study because we need better ways for computers and people to communicate. People’s feelings play a significant role in their conversations. It could be useful for machines to recognize and respond to human emotions in various areas, such as healthcare, education, customer service, and virtual assistants. Deep learning technologies have made significant strides in recent years, improving the performance of systems that handle speech-related tasks. SER has also seen major advancements due to the development of complex neural network designs. This paper offers an in-depth look at current research in SER, focusing on studies that use deep learning techniques. It compares the most effective models, including convolutional neural networks (CNNs), long short-term memory (LSTM) networks, transformers, and hybrid models. This study also talks about the most important things that affect SER performance, such as choosing speech emotion datasets and features. This review additionally discusses about the problems and limitations that current SER research faces. For example, datasets are not very diverse, emotions are hard to represent, speakers and languages are dependent on each other, and it is hard to use the technology in real time. This paper seeks to provide substantial insights for researchers on SER by synthesizing findings from multiple recent studies.

Speech emotion recognition has received an increasing interest in recent years, which is often conducted on the assumption that speech utterances in training and testing datasets are obtained under the same conditions. However, in reality, this assumption does not hold as the speech data are often collected from different devices or environments. Hence, there exists discrepancy between the training and testing data, which will have an adverse effect on recognition performance. In this paper, we examine the problem of cross-corpus speech emotion recognition. To address it, we present a novel transfer linear subspace learning (TLSL) framework to learn a common feature subspace for source and target datasets. In TLSL, a nearest neighbor graph algorithm is used to measure the similarity between different corpora, and a feature grouping strategy is introduced to divide the emotional features into two categories, i.e., high transferable part (HTP) versus low transferable part (LTP). To explore the proposed TLSL with different scenarios, we propose two kinds of TLSL approaches, called transfer unsupervised linear subspace learning (TULSL) and transfer supervised linear subspace learning (TSLSL), and provide the corresponding solutions for the optimization problems. Extensive experiments on several benchmark datasets validate the effectiveness of TLSL for cross-corpus speech emotion recognition.

Cross-corpus speech emotion recognition based on transfer non-negative matrix factorization

Speech emotion recognition (SER) is a hot topic in academia. One of the key issues in improving the performance of SER systems is the choice of speech emotion features. In order to establish a robust speech emotion recognition system, it is essential to select the features which can be a perfect representation of speech emotion attributes. Researchers has done a lot of work, proposed a variety of emotional features and made great progress. Although each kind of features were proven to be effective, most of methods are based on a single type. In this paper, we proposed a method of feature fusion based on deep learning, combining spectral-based features and pitch-based hyper-prosodic features. The experiments show that this method improves the performance of speech emotion recognition system.

Over the past years, speech emotion recognition (SER) studies have been gaining much interest in the fields of affective computing and human-computer interaction (HCI). The idea was to improve the interaction between human beings and machines. In this paper, an SER system that classifies and recognise six basic emotions (anger, sadness, disgust, fear, happiness, and neutral) from speech spoken in Sepedi language (one of South Africa's official languages) is discussed. Speech recordings were collected from the Sepedi language speakers and TV drama broadcast to create emotional speech corpora. 34 speech features were then extracted from the speech corpora, using the pyAudioAnalysis tool, to train and compare different algorithms using 10 folds cross-validation. The experiments were conducted using WEKA data-mining software. The results showed that Auto-WEKA outperforms all the standard algorithms (SVM. KNN and MLP). Recorded speech corpus yielded good recognition accuracy compare to TV broadcast speech corpus.