Audio Deepfakes, which are highly realistic fake audio recordings driven by AI tools that clone human voices, With Advancements in Text-Based Speech Generation (TTS) and Vocal Conversion (VC) technologies have enabled...
详细信息
Audio Deepfakes, which are highly realistic fake audio recordings driven by AI tools that clone human voices, With Advancements in Text-Based Speech Generation (TTS) and Vocal Conversion (VC) technologies have enabled it easier to create realistic synthetic and imitative speech, making audio Deepfakes a common and potentially dangerous form of deception. Well-known people, like politicians and celebrities, are often targeted. They get tricked into saying controversial things in fake recordings, causing trouble on social media. Even kids’ voices are cloned to scam parents into ransom payments, etc. Therefore, developing effective algorithms to distinguish Deepfake audio from real audio is critical to preventing such frauds. Various Machine learning (ML) and Deep learning (DL) techniques have been created to identify audio Deepfakes. However, most of these solutions are trained on datasets in English, Portuguese, French, and Spanish, expressing concerns regarding their correctness for other languages. The main goal of the research presented in this paper is to evaluate the effectiveness of deep learning neural networks in detecting audio Deepfakes in the Urdu language. Since there’s no suitable dataset of Urdu audio available for this purpose, we created our own dataset (URFV) utilizing both genuine and fake audio recordings. The Urdu Original/real audio recordings were gathered from random youtube podcasts and generated as Deepfake audios using the RVC model. Our dataset has three versions with clips of 5, 10, and 15 seconds. We have built various deep learning neural networks like (RNN+LSTM, CNN+attention, TCN, CNN+RNN) to detect Deepfake audio made through imitation or synthetic techniques. The proposed approach extracts Mel-Frequency-Cepstral-Coefficients (MFCC) features from the audios in the dataset. When tested and evaluated, Our models’ accuracy across datasets was noteworthy. 97.78% (5s), 98.89% (10s), and 98.33% (15s) were remarkable results for the RNN+LSTM
Effective data management is crucial in navigating any health crisis. With proper data management protocols in place, stakeholders can swiftly adapt to evolving circumstances during challenging times. A recent event l...
详细信息
Suicide represents a poignant societal issue deeply entwined with mental well-being. While existing research primarily focuses on identifying suicide-related texts, there is a gap in the advanced detection of mental h...
详细信息
In this paper, we propose a deep learning-based model, called Weight and Attention Network (WANet), for video summarization. The network comprises a simple multi-head attention mechanism, followed by a feed-forward ne...
详细信息
This paper presents a novel approach to optimise resource allocation in virtualised systems, aiming to maximise performance and minimise operational expenses. Leveraging deep learning models, specifically long-short-t...
详细信息
The cellular automaton (CA), a discrete model, is gaining popularity in simulations and scientific exploration across various domains, including cryptography, error-correcting codes, VLSI design and test pattern gener...
详细信息
Most social networks allow connections amongst many people based on shared *** networks have to offer shared data like videos,photos with minimum latency to the group,which could be challenging as the storage cost has...
详细信息
Most social networks allow connections amongst many people based on shared *** networks have to offer shared data like videos,photos with minimum latency to the group,which could be challenging as the storage cost has to be minimized and hence entire data replication is not a *** replication of data across a network of read-intensive can potentially lead to increased savings in cost and energy and reduce the end-user’s response *** simple and adaptive replication strategies exist,the solution is non-deter-ministic;the replicas of the data need to be optimized to the data usability,perfor-mance,and stability of the application *** resolve the non-deterministic issue of replication,metaheuristics are *** this work,Harmony Search and Tabu Search algorithms are used optimizing the replication process.A novel Har-mony-Tabu search is proposed for effective placement and replication of *** on large datasets show the effectiveness of the proposed *** is seen that the bandwidth saving for proposed harmony-Tabu replication per-forms better in the range of 3.57%to 18.18%for varying number of cloud data-centers when compared to simple replication,Tabu replication and Harmony replication algorithm.
People across the world aspire to settle in urban areas for better opportunities in career, education, and healthcare facilities. The increased proportion of people living in urban areas requires an improvement of sma...
详细信息
Federated Learning (FL) has emerged as a promising approach to address the challenges of data privacy, security, and scalability in Internet of Things (IoT) environments. This paper provides a comprehensive survey of ...
详细信息
Purpose: The rapid spread of COVID-19 has resulted in significant harm and impacted tens of millions of people globally. In order to prevent the transmission of the virus, individuals often wear masks as a protective ...
详细信息
暂无评论