In the context of multi-depot operations in the fast-moving consumer goods (FMCGs) industry, traditional logistics approaches increasingly fail to meet integrated requirements for cost, speed and environmental impact. Multi-depot collaboration, key to enhancing efficiency, faces challenges in route optimization, inventory management and carbon constraints. To balance economy and sustainability, this paper addresses multi-depot distribution challenges via the collaborative delivery vehicle routing problem with multi-depots and replenishment (CDVRP-MDR). It constructs a mixed-integer linear programming model with vehicle capacity and carbon constraints, then designs an adaptive large neighborhood search–artificial bee colony algorithm (ALNS–ABC). Through dynamic destruction-repair operator selection and gene reverse-order recombination, ALNS–ABC optimizes local search to balance global exploration and local development. Benchmark experiments confirm its effectiveness in multi-depot optimization. For FMCG firms’ centralized inventory issues (delayed transfers, high long-haul costs), it boosts inventory turnover and cross-depot response via collaborative transfers, offering a practical paradigm for green upgrading of multi-depot logistics systems.

With the rapid development of cities and the increase in the number of motor vehicles, traditional intelligent traffic video analytics systems face a significant challenge due to soaring computational demands and limited network transmission resources. Today’s widely used cloud-based traffic video analytics system, which is generally reliant on transmitting all video data to centralized cloud servers, suffer from high latency during network fluctuations and inability to respond promptly to urban traffic management. This paper introduces a cloud-edge collaborative framework for traffic video analytics. Within this framework, edge servers serve as intermediaries between video sources and the cloud center. The framework prioritizes the offloading of computing tasks to nodes located near the video sources, rationally leveraging the limited computing and network resources to mitigate network transmission load. We develop a measurement-based analytical model to describe the trade-offs among network latency, inference latency, and analytics accuracy in edge-based real-time video analytics system. As a core element of our approach, we present a resolution selection and bandwidth allocation algorithm based on Lyapunov optimization and heuristic search, designed to dynamically adjust video resolution and distribute bandwidth between edge and cloud servers to balance latency and accuracy without requiring future information. Experiments on a cloud-edge collaborative video analytics system demonstrate the algorithm’s effectiveness in substantially enhancing accuracy and responsiveness.

Service level agreements (SLAs) formulated by cloud rendering service providers and users are varied, as users may have diverse performance requirements for their own jobs. This leads to a complex issue that cloud resources need to be allocated to rendering jobs in an appropriate and effective manner to satisfy users' diverse SLAs. To address this issue, in this paper, we propose a novel fair and efficient resource allocation algorithm, which aims to maximize the execution efficiency of rendering service applications while satisfying users' diverse SLAs. Firstly, to satisfy users' diverse SLAs, we propose a rigorous definition ofweighted acceleration ratio fairness, whose guiding principle is that the execution speed of a rendering job should be proportional to its weight determined by users' SLAs. Then, under the guidance of the proposed principle of acceleration ratio fairness, we formulate a new algorithm to fairly allocate resources to rendering jobs. Lastly, to improve execution efficiency and coordinate efficiency and fairness, we propose a fair and efficient resource allocation algorithm with relaxing fairness in resource competitive and non-competitive situations separately for rendering service applications. With extensive experiments that involve real rendering application workloads, we validate the effectiveness of our algorithms in improving execution efficiency and satisfying users' diverse SLAs.

Text normalization, defined as a procedure transforming nonstandard words to spoken-form words, is crucial to the intelligibility of synthesized speech in text-to-speech system. Rule-based methods without considering context can not eliminate ambiguation, whereas sequence-to-sequence neural network based methods suffer from the unexpected and uninterpretable errors problem. Recently proposed hybrid system treats rule-based model and neural model as two cascaded sub-modules, where limited interaction capability makes neural network model cannot fully utilize expert knowledge contained in the rules. Inspired by Flat-LAttice Transformer (FLAT), we propose an end-to-end Chinese text normalization model, which accepts Chinese characters as direct input and integrates expert knowledge contained in rules into the neural network, both contribute to the superior performance of proposed model for the text normalization task. We also release a first publicly accessible large-scale dataset for Chinese text normalization. Our proposed model has achieved excellent results on this dataset.

Singing voice synthesis has been paid rising attention with the rapid development of speech synthesis area. In general, a studio-level singing corpus is usually necessary to produce a natural singing voice from lyrics and music-related transcription. However, such a corpus is difficult to collect since it's hard for many of us to sing like a professional singer. In this paper, we propose an approach - Learn2Sing that only needs a singing teacher to generate the target speakers' singing voice without their singing voice data. In our approach, a teacher's singing corpus and speech from multiple target speakers are trained in a frame-level auto-regressive acoustic model where singing and speaking share the common speaker embedding and style tag embedding. Meanwhile, since there is no music-related transcription for the target speaker, we use log-scale fundamental frequency (LF0) as an auxiliary feature as the inputs of the acoustic model for building a unified input representation. In order to enable the target speaker to sing without singing reference audio in the inference stage, a duration model and an LF0 prediction model are also trained. Particularly, we employ domain adversarial training (DAT) in the acoustic model, which aims to enhance the singing performance of target speakers by disentangling style from acoustic features of singing and speaking data. Our experiments indicate that the proposed approach is capable of synthesizing singing voice for target speaker given only their speech samples.

Automatic speech recognition (ASR) has been significantly advanced with the use of deep learning and big data. How-ever improving robustness, including achieving equally good performance on diverse speakers and accents, is still a challenging problem. In particular, the performance of children speech recognition (CSR) still lags behind due to 1) the speech and language characteristics of children's voice are substantially different from those of adults and 2) sizable open dataset for children speech is still not available in the research community. To address these problems, we launch the Children Speech Recognition Challenge (CSRC), as a flagship satellite event of IEEE SLT 2021 workshop. The challenge will release about 400 hours of Mandarin speech data for registered teams and set up two challenge tracks and provide a common testbed to benchmark the CSR performance. In this paper, we introduce the datasets, rules, evaluation method as well as baselines.

Performance analysis is important for service clouds serving composite service application jobs containing parallelizable tasks, for optimizing the degree of parallelism (DOP) and resource allocation schemes could improve performance obviously. In this paper, we describe a novel tandem queuing network with a parallel multi-station multi-server system as an analytical model for service clouds serving composite service application jobs. We design a partition method (termed the 'pleasing partition') to help us propose an analytical model for parallelizable service which is the vital fraction of composite service. After that, we could obtain a complete probability distribution of response time, waiting time and other important performance metrics calculated by our proposed analytical model. Thus, to use this model, cloud operators could determine proper job configurations and resource allocation schemes, for achieving specific QoS (Quality of Service). Extensive simulations are conducted to validate that our analytical model has high accuracy in predicting performance metrics of composite service application jobs.

Performance analysis is crucial to the successful development of cloud computing paradigm. And it is especially important for a cloud computing center serving parallelizable application jobs, for determining a proper degree of parallelism could reduce the mean service response time and thus improve the performance of cloud computing obviously. In this paper, taking the cloud based rendering service platform as an example application, we propose an approximate analytical model for cloud computing centers serving parallelizable jobs using M/M/c/r queuing systems, by modeling the rendering service platform as a multi-station multi-server system. We solve the proposed analytical model to obtain a complete probability distribution of response time, blocking probability and other important performance metrics for given cloud system settings. Thus this model can guide cloud operators to determine a proper setting, such as the number of servers, the buffer size and the degree of parallelism, for achieving specific performance levels. Through extensive simulations based on both synthetic data and real-world workload traces, we show that our proposed analytical model can provide approximate performance prediction results for cloud computing centers serving parallelizable jobs, even those job arrivals follow different distributions.