During the last decade, Speech Emotion Recognition (SER) has emerged as an integral component within Human-computer Interaction (HCI) and other high-end speech processing systems. Generally, an SER system targets the speaker's existence of varied emotions by extracting and classifying the prominent features from a preprocessed speech signal. However, the way humans and machines recognize and correlate emotional aspects of speech signals are quite contrasting quantitatively and qualitatively, which present enormous difficulties in blending knowledge from interdisciplinary fields, particularly speech emotion recognition, applied psychology, and human-computer interface. The paper carefully identifies and synthesizes recent relevant literature related to the SER systems' varied design components/methodologies, thereby providing readers with a state-of-the-art understanding of the hot research topic. Furthermore, while scrutinizing the current state of understanding on SER systems, the research gap's prominence has been sketched out for consideration and analysis by other related researchers, institutions, and regulatory bodies.

The rise of AI-generated synthetic media, or deepfakes, has introduced unprecedented opportunities and challenges across various fields, including entertainment, cybersecurity, and digital communication. Using advanced frameworks such as Generative Adversarial Networks (GANs) and Diffusion Models (DMs), deepfakes are capable of producing highly realistic yet fabricated content, while these advancements enable creative and innovative applications, they also pose severe ethical, social, and security risks due to their potential misuse. The proliferation of deepfakes has triggered phenomena like “Impostor Bias”, a growing skepticism toward the authenticity of multimedia content, further complicating trust in digital interactions. This paper is mainly based on the description of a research project called FF4ALL (FF4ALL-Detection of Deep Fake Media and Life-Long Media Authentication) for the detection and authentication of deepfakes, focusing on areas such as forensic attribution, passive and active authentication, and detection in real-world scenarios. By exploring both the strengths and limitations of current methodologies, we highlight critical research gaps and propose directions for future advancements to ensure media integrity and trustworthiness in an era increasingly dominated by synthetic media.

Audio deepfake detection is emerging as a crucial field in digital media, as distinguishing real audio from deepfakes becomes increasingly challenging due to the advancement of deepfake technologies. These methods threaten information authenticity and pose serious security risks. Addressing this challenge, we propose a novel architecture that combines Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) for effective deepfake audio detection. Our approach is distinguished by the feature concatenation of a comprehensive set of acoustic features: Mel Frequency Cepstral Coefficients (MFCC), Mel spectrograms, Constant Q Cepstral Coefficients (CQCC), and Constant-Q Transform (CQT) vectors. In the proposed architecture, features processed by a CNN are concatenated into two multi-dimensional features for comprehensive analysis, then analyzed by a BiLSTM network to capture temporal dynamics and contextual dependencies in audio data. This synergistic method ensures an understanding of both spatial and sequential audio characteristics. We validate our model on the ASVSpoof 2019 and FoR datasets, using accuracy and Equal Error Rate (EER) metrics for the evaluation.

The rise of audio deepfakes presents a significant security threat that undermines trust in digital communications and media. These synthetic audio technologies can convincingly mimic a person’s voice, enabling malicious activities like impersonation, fraud, and misinformation. Addressing this growing threat requires robust detection systems to ensure the authenticity of digital content. In this survey, we provide a comprehensive analysis of the state-of-the-art techniques in audio deepfake generation and detection. We examine various methods used to generate audio deepfakes, including Text-to-Speech (TTS) and Voice Conversion (VC) technologies, and discuss their capabilities in producing highly realistic synthetic audio. On the detection front, we explore a wide range of approaches, encompassing traditional machine learning and deep learning models for feature extraction and classification. The importance of publicly available datasets for training and evaluating these models is emphasized, showcasing their role in advancing detection capabilities. Additionally, the integration of audio and video deepfake detection systems is discussed, providing a comprehensive defense against sophisticated attacks. This survey critically assesses existing methods and datasets, highlighting challenges like the high realism of deepfakes, limited data diversity, and the need for models that generalize well. It aims to guide future research in enhancing detection and safeguarding digital media integrity.