Human-computer interaction (HCI) has seen a paradigm shift from textual or display-based control toward more intuitive control modalities such as voice, gesture, and mimicry. Particularly, speech has a great deal of information, conveying information about the speaker’s inner condition and his/her aim and desire. While word analysis enables the speaker’s request to be understood, other speech features disclose the speaker’s mood, purpose, and motive. As a result, emotion recognition from speech has become critical in current human-computer interaction systems. Moreover, the findings of the several professions involved in emotion recognition are difficult to combine. Many sound analysis methods have been developed in the past. However, it was not possible to provide an emotional analysis of people in a live speech. Today, the development of artificial intelligence and the high performance of deep learning methods bring studies on live data to the fore. This study aims to detect emotions in the human voice using artificial intelligence methods. One of the most important requirements of artificial intelligence works is data. The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) open-source dataset was used in the study. The RAVDESS dataset contains more than 2000 data recorded as speeches and songs by 24 actors. Data were collected for eight different moods from the actors. It was aimed at detecting eight different emotion classes, including neutral, calm, happy, sad, angry, fearful, disgusted, and surprised moods. The multilayer perceptron (MLP) classifier, a widely used supervised learning algorithm, was preferred for classification. The proposed model’s performance was compared with that of similar studies, and the results were evaluated. An overall accuracy of 81% was obtained for classifying eight different emotions by using the proposed model on the RAVDESS dataset.

Recognizing human emotions by machines is a complex task. Deep learning models attempt to automate this process by rendering machines to exhibit learning capabilities. However, identifying human emotions from speech with good performance is still challenging. With the advent of deep learning algorithms, this problem has been addressed recently. However, most research work in the past focused on feature extraction as only one method for training. In this research, we have explored two different methods of extracting features to address effective speech emotion recognition. Initially, two-way feature extraction is proposed by utilizing super convergence to extract two sets of potential features from the speech data. For the first set of features, principal component analysis (PCA) is applied to obtain the first feature set. Thereafter, a deep neural network (DNN) with dense and dropout layers is implemented. In the second approach, mel-spectrogram images are extracted from audio files, and the 2D images are given as input to the pre-trained VGG-16 model. Extensive experiments and an in-depth comparative analysis over both the feature extraction methods with multiple algorithms and over two datasets are performed in this work. The RAVDESS dataset provided significantly better accuracy than using numeric features on a DNN.

Several speaker recognition algorithms failed to get the best results because of the wildly varying datasets and feature sets for classification. Gender information helps reduce this effort since categorizing the classes based on gender may help lessen the impact of gender variability on the retrieved features. This study attempted to construct a perfect classification model for language‐independent gender identification utilizing the Common Voice dataset (Mozilla). Most previous studies are doing manual extracting characteristics and feeding them into a machine learning model for categorization. Deep neural networks (DNN) were the most effective strategy in our research. Nonetheless, the main goal was to take advantage of the wealth of information included in voice data without requiring significant manual intervention. We trained the deep learning network to choose essential information from speech spectrograms for the classification layer, performing gender detection. The pretrained ResNet 50 fine‐tuned gender data successfully achieved an accuracy of 98.57% better than the traditional ML approaches and the previous works reported with the same dataset. Furthermore, the model performs well on additional datasets, demonstrating the approach’s generalization capacity.

Food production is a growing challenge with the increasing global population. To increase the yield of food production, we need to adopt new biotechnology-based fertilization techniques. Furthermore, we need to improve early prevention steps against plant disease. Guava is an essential fruit in Asian countries such as Pakistan, which is fourth in its production. Several pathological and fungal diseases attack guava plants. Furthermore, postharvest infections might result in significant output losses. A professional opinion is essential for disease analysis due to minor variances in various guava disease symptoms. Farmers’ poor usage of pesticides may result in financial losses due to incorrect diagnosis. Computer-vision-based monitoring is required with developing field guava plants. This research uses a deep convolutional neural network (DCNN)-based data enhancement using color-histogram equalization and the unsharp masking technique to identify different guava plant species. Nine angles from 360${}^{\circ }$ were applied to increase the number of transformed plant images. These augmented data were then fed as input into state-of-the-art classification networks. The proposed method was first normalized and preprocessed. A locally collected guava disease dataset from Pakistan was used for the experimental evaluation. The proposed study uses five neural network structures, AlexNet, SqueezeNet, GoogLeNet, ResNet-50, and ResNet-101, to identify different guava plant species. The experimental results proved that ResNet-101 obtained the highest classification results, with 97.74% accuracy.

Emotions play an essential role in human relationships, and many real-time applications rely on interpreting the speaker’s emotion from their words. Speech emotion recognition (SER) modules aid human-computer interface (HCI) applications, but they are challenging to implement because of the lack of balanced data for training and clarity about which features are sufficient for categorization. This research discusses the impact of the classification approach, identifying the most appropriate combination of features and data augmentation on speech emotion detection accuracy. Selection of the correct combination of handcrafted features with the classifier plays an integral part in reducing computation complexity. The suggested classification model, a 1D convolutional neural network (1D CNN), outperforms traditional machine learning approaches in classification. Unlike most earlier studies, which examined emotions primarily through a single language lens, our analysis looks at numerous language data sets. With the most discriminating features and data augmentation, our technique achieves 97.09%, 96.44%, and 83.33% accuracy for the BAVED, ANAD, and SAVEE data sets, respectively.

Sign language is the native language of deaf people, which they use in their daily life, and it facilitates the communication process between deaf people. The problem faced by deaf people is targeted using sign language technique. Sign language refers to the use of the arms and hands to communicate, particularly among those who are deaf. This varies depending on the person and the location from which they come. As a result, there is no standardization about the sign language to be used; for example, American, British, Chinese, and Arab sign languages are all distinct. Here, in this study we trained a model, which will be able to classify the Arabic sign language, which consists of 32 Arabic alphabet sign classes. In images, sign language is detected through the pose of the hand. In this study, we proposed a framework, which consists of two CNN models, and each of them is individually trained on the training set. The final predictions of the two models were ensembled to achieve higher results. The dataset used in this study is released in 2019 and is called as ArSL2018. It is launched at the Prince Mohammad Bin Fahd University, Al Khobar, Saudi Arabia. The main contribution in this study is resizing the images to 64 ∗ 64 pixels, converting from grayscale images to three-channel images, and then applying the median filter to the images, which acts as lowpass filtering in order to smooth the images and reduce noise and to make the model more robust to avoid overfitting. Then, the preprocessed image is fed into two different models, which are ResNet50 and MobileNetV2. ResNet50 and MobileNetV2 architectures were implemented together. The results we achieved on the test set for the whole data are with an accuracy of about 97% after applying many preprocessing techniques and different hyperparameters for each model, and also different data augmentation techniques.