Multimodal interaction is a transformative human-computer interaction (HCI) approach that allows users to interact with systems through various communication channels such as speech, gesture, touch, and gaze. With advancements in sensor technology and machine learning (ML), multimodal systems are becoming increasingly important in various applications, including virtual assistants, intelligent environments, healthcare, and accessibility technologies. This survey concisely overviews recent advancements in multimodal interaction, interfaces, and communication. It delves into integrating different input and output modalities, focusing on critical technologies and essential considerations in multimodal fusion, including temporal synchronization and decision-level integration. Furthermore, the survey explores the challenges of developing context-aware, adaptive systems that provide seamless and intuitive user experiences. Lastly, by examining current methodologies and trends, this study underscores the potential of multimodal systems and sheds light on future research directions.

Emotion recognition from speech may play a crucial role in many applications related to human–computer interaction or understanding the affective state of users in certain tasks, where other modalities such as video or physiological parameters are unavailable. In general, a human’s emotions may be recognized using several modalities such as analyzing facial expressions, speech, physiological parameters (e.g., electroencephalograms, electrocardiograms) etc. However, measuring of these modalities may be difficult, obtrusive or require expensive hardware. In that context, speech may be the best alternative modality in many practical applications. In this work we present an approach that uses a Convolutional Neural Network (CNN) functioning as a visual feature extractor and trained using raw speech information. In contrast to traditional machine learning approaches, CNNs are responsible for identifying the important features of the input thus, making the need of hand-crafted feature engineering optional in many tasks. In this paper no extra features are required other than the spectrogram representations and hand-crafted features were only extracted for validation purposes of our method. Moreover, it does not require any linguistic model and is not specific to any particular language. We compare the proposed approach using cross-language datasets and demonstrate that it is able to provide superior results vs. traditional ones that use hand-crafted features.

Deep Learning has dramatically advanced the state of the art in vision, speech and many other areas. Recently, numerous deep learning algorithms have been proposed to solve traditional artificial intelligence problems. In this paper, in order to detect the version that can provide the best trade-off in terms of time and accuracy, convolutional networks of various depths have been implemented. Batch normalization is also considered since it acts as a regularizer and achieves the same accuracy with fewer training steps. For maximizing the yield of the complexity by diminishing, as well as minimizing the loss of accuracy, LSTM neural net layers are utilized in the process. The image sequences are proven to be classified by the LSTM in a more accelerated manner, while managing better precision. Concretely, the more complex the CNN, the higher the percentages of exactitude; in addition, but for the high-rank increase in accuracy, the time was significantly decreased, which eventually rendered the trade-off optimal. The average improvement of performance for all models regarding both datasets used amounted to $42\%$ .