In this paper, the problem of joint transmission and computation resource allocation for a multi-user probabilistic semantic communication (PSC) network is investigated. In the considered model, users employ semantic ...
详细信息
ISBN:
(纸本)9798350304060;9798350304053
In this paper, the problem of joint transmission and computation resource allocation for a multi-user probabilistic semantic communication (PSC) network is investigated. In the considered model, users employ semantic information extraction techniques to compress their large-sized raw data before transmitting them to a multi-antenna base station (BS). Our model represents the raw data through comprehensive knowledge graphs, utilizing shared probability graphs between users and the BS for efficient semantic compression. The resource allocation problem is formulated as an optimization problem with the objective of maximizing the sum of equivalent rate of all users, considering total power budget constraint. This joint optimization problem inherently addresses the delicate balance between transmission efficiency and computational complexity. To address this optimization challenge, we present an iterative algorithm in which the optimal solution for the semantic compression ratio of a specific user is determined at each iteration. Numerical results validate the effectiveness of the proposed scheme.
Cloud-based dataprocessing latency mainly depends on the transmission delay of data to the cloud and the used dataprocessing algorithm. To minimize the transmission delay, it is important to compress the transferred...
详细信息
ISBN:
(纸本)9798350399462
Cloud-based dataprocessing latency mainly depends on the transmission delay of data to the cloud and the used dataprocessing algorithm. To minimize the transmission delay, it is important to compress the transferred data without reducing the quality of the data. When using datacompression algorithms, it is important to validate the impact of these algorithms on the detection quality. This work evaluates the effects of image compression and transmission over wireless interfaces on state of the art neural networks. Therefore, a modern image processing platform for next generation automotive processing architectures, as used in software defined vehicles, is introduced. The impacts of different image encoders as well as data transmission parameters are investigated and discussed.
In response to the demand for data transmission efficiency and accuracy for the diversity of power line carrier services in China, an adaptive datacompression scheme is introduced in the paper, which is trained to co...
详细信息
In this paper, we propose a novel efficient digital twin (DT) dataprocessing scheme to reduce service latency for multicast short video streaming. Particularly, DT is constructed to emulate and analyze user status fo...
详细信息
ISBN:
(纸本)9798350378412
In this paper, we propose a novel efficient digital twin (DT) dataprocessing scheme to reduce service latency for multicast short video streaming. Particularly, DT is constructed to emulate and analyze user status for multicast group update and swipe feature abstraction. Then, a precise measurement model of DT dataprocessing is developed to characterize the relationship among DT model size, user dynamics, and user clustering accuracy. A service latency model, consisting of DT dataprocessing delay, video transcoding delay, and multicast transmission delay, is constructed by incorporating the impact of user clustering accuracy. Finally, a joint optimization problem of DT model size selection and bandwidth allocation is formulated to minimize the service latency. To efficiently solve this problem, a diffusion-based resource management algorithm is proposed, which utilizes the denoising technique to improve the action-generation process in the deep reinforcement learning algorithm. Simulation results based on the real-world dataset demonstrate that the proposed DT dataprocessing scheme outperforms benchmark schemes in terms of service latency.
Homomorphic encryption (HE) algorithms, particularly the Cheon-Kim-Kim-Song (CKKS) scheme, offer significant potential for secure computation on encrypted data, making them valuable for privacy-preserving machine lear...
详细信息
ISBN:
(纸本)9798350387186;9798350387179
Homomorphic encryption (HE) algorithms, particularly the Cheon-Kim-Kim-Song (CKKS) scheme, offer significant potential for secure computation on encrypted data, making them valuable for privacy-preserving machine learning. However, high latency in large integer operations in the CKKS algorithm hinders the processing of large datasets and complex computations. This paper proposes a novel strategy that combines lossless datacompression techniques with the parallel processing power of graphics processing units to address these challenges. Our approach demonstrably reduces data size by 90% and achieves significant speedups of up to 100 times compared to conventional approaches. This method ensures data confidentiality while mitigating performance bottlenecks in CKKS-based computations, paving the way for more efficient and scalable HE applications.
A great amount of endeavour has recently been devoted to device activity detection in massive machine-type communications. This paper targets at a practical issue: communication-efficient joint signal compression and ...
详细信息
ISBN:
(纸本)9781538674628
A great amount of endeavour has recently been devoted to device activity detection in massive machine-type communications. This paper targets at a practical issue: communication-efficient joint signal compression and activity detection in cell-free massive MIMO with capacity-limited front-hauls. To this end, we propose a novel deep learning framework which jointly optimizes the compression modules, quantization modules at the access points, and the decompression module and detection module at the central processing unit. Specifically, deep unfolding is leveraged for designing the detection module in order to inherit the domain knowledge derived from the optimization algorithm, and the other modules are constructed by generic layers for increasing the learning capability. A joint training strategy is proposed to optimize all the modules in an end-to-end manner. Numerical results demonstrate the superiority of the proposed end-to-end learning framework compared with classical optimization methods.
This study proposes a new compression algorithm for health data management, which is a derivative of the JPEG algorithm. The proposed method has shown improvement in compression ratio compared to the classical JPEG al...
详细信息
Code-mixing is the situation where words and phrases from two or more different languages are used interchangeably within one sentence or utterance. With the increasing number of bilinguals and multilinguals in today&...
详细信息
ISBN:
(纸本)9798350350463;9798350350456
Code-mixing is the situation where words and phrases from two or more different languages are used interchangeably within one sentence or utterance. With the increasing number of bilinguals and multilinguals in today's world, there is heavy evidences of code-mixing in many scenarios. However their presence affects the accuracy of current natural language processing and speech processing systems, since currently available speech-to-text and text-to-speech systems are not viable to translate speech which consists of two or more languages mixed together to a target language, as they assume the text and speech to all come from a single language. In the case of Dravidian languages, especially Kannada-English code-mixing, there are very few datasets available, and lesser so which consist of speech data. In order to get closer to rectifying this problem, we present a generative adversarial architecture to synthesize code-mixed speech in Kannada-English using monolingual utterances in Kannada. We are able to generate sentences with a good FAD (Frechet Audio Distance) score of around 14.490, using a very small training dataset.
Future telecommunication networks, including 5G and 6G, envision the co-existence of public and private networks with access to a massive number of wireless devices. In practice, such a network leads to serious interf...
详细信息
ISBN:
(纸本)9798350350463;9798350350456
Future telecommunication networks, including 5G and 6G, envision the co-existence of public and private networks with access to a massive number of wireless devices. In practice, such a network leads to serious interference from concurrent transmission in closely separated frequency bands which leads to adjacent channel interference (ACI). The ill-effects of the interference can be mitigated by having a comprehensive understanding of the interference relation between the wireless devices. However, existing approaches are not equipped to identify the devices causing interference. In this work, we model the interference in the network as a graph with devices as nodes and edges representing interference relations. We propose neural network architectures to predict the interference graph. The proposed models are trained and tested for ACI graphs on co-existing private and public network data. The best-performing model accurately predicts the interference graph and generalizes well across different numbers of wireless devices with an average AUROC of 0.92.
Extensive use of voice assistants by children in their day-to-day life activities demand for better performance of Automatic Speech Recognition (ASR) for children's speech. The recent advancements in ASR perform b...
详细信息
ISBN:
(纸本)9798350350463;9798350350456
Extensive use of voice assistants by children in their day-to-day life activities demand for better performance of Automatic Speech Recognition (ASR) for children's speech. The recent advancements in ASR perform better for adult speech. However, due to acoustic mismatch (in particular, higher F0 and thus, poor spectral resolution, and less availability of children data), it remains a challenge to improve the performance of children's ASR. In this context, a shared task on ASR for children's speech 2021 was organized during INTERSPEECH 2021. In this paper, the voice conversion-based data augmentation technique using a cycle-consistent generative adversarial network (CycleGAN) is investigated for closed track in the challenge. Here, CycleGAN training is exploited for children-to-children voice conversion. Training of CycleGAN and ASR experiments are performed on the speech data provided during the challenge. In our experiments, CycleGAN-based data augmentation showed a relative improvement of 9% and 3% in WER compared to the baseline system on the Dev and Eval sets, respectively. This work may find its significance in ASR for low resource languages, where Librispeech or any other external dataset is not an option.
暂无评论