We propose a general framework to compute the word error rate (WER) of ASR systems that process recordings containing multiple speakers at their input and that produce multiple output word sequences (MIMO). Such ASR systems are typically required, e.g., for meeting transcription. We provide an efficient implementation based on a dynamic programming search in a multi-dimensional Levenshtein distance tensor under the constraint that a reference utterance must be matched consistently with one hypothesis output. This also results in an efficient implementation of the ORC WER which previously suffered from exponential complexity. We give an overview of commonly used WER definitions for multi-speaker scenarios and show that they are specializations of the above MIMO WER tuned to particular application scenarios. We conclude with a discussion of the pros and cons of the various WER definitions and a recommendation when to use which.
相關內容
Memory corruption attacks (MCAs) refer to malicious behaviors of system intruders that modify the contents of a memory location to disrupt the normal operation of computing systems, causing leakage of sensitive data or perturbations to ongoing processes. Unlike general-purpose systems, unmanned systems cannot deploy complete security protection schemes, due to their limitations in size, cost and performance. MCAs in unmanned systems are particularly difficult to defend against. Furthermore, MCAs have diverse and unpredictable attack interfaces in unmanned systems, severely impacting digital and physical sectors. In this paper, we first generalize, model and taxonomize MCAs found in unmanned systems currently, laying the foundation for designing a portable and general defense approach. According to different attack mechanisms, we found that MCAs are mainly categorized into two types--return2libc and return2shellcode. To tackle return2libc attacks, we model the erratic operation of unmanned systems with cycles and then propose a cycle-task-oriented memory protection (CToMP) approach to protect control flows from tampering. To defend against return2shellcode attacks, we introduce a secure process stack with a randomized memory address by leveraging the memory pool to prevent Shellcode from being executed. Moreover, we discuss the mechanism by which CToMP resists the ROP attack, a novel variant of return2libc attacks. Finally, we implement CToMP on CUAV V5+ with Ardupilot and Crazyflie. The evaluation and security analysis results demonstrate that the proposed approach CToMP is resilient to various MCAs in unmanned systems with low footprints and system overhead.
Achieving real-time capability is an essential prerequisite for the industrial implementation of nonlinear model predictive control (NMPC). Data-driven model reduction offers a way to obtain low-order control models from complex digital twins. In particular, data-driven approaches require little expert knowledge of the particular process and its model, and provide reduced models of a well-defined generic structure. Herein, we apply our recently proposed data-driven reduction strategy based on Koopman theory [Schulze et al. (2022), Comput. Chem. Eng.] to generate a low-order control model of an air separation unit (ASU). The reduced Koopman model combines autoencoders and linear latent dynamics and is constructed using machine learning. Further, we present an NMPC implementation that uses derivative computation tailored to the fixed block structure of reduced Koopman models. Our reduction approach with tailored NMPC implementation enables real-time NMPC of an ASU at an average CPU time decrease by 98 %.
Wireless communication systems to date primarily rely on the orthogonality of resources to facilitate the design and implementation, from user access to data transmission. Emerging applications and scenarios in the sixth generation (6G) wireless systems will require massive connectivity and transmission of a deluge of data, which calls for more flexibility in the design concept that goes beyond orthogonality. Furthermore, recent advances in signal processing and learning have attracted considerable attention, as they provide promising approaches to various complex and previously intractable problems of signal processing in many fields. This article provides an overview of research efforts to date in the field of signal processing and learning for next-generation multiple access, with an emphasis on massive random access and non-orthogonal multiple access. The promising interplay with new technologies and the challenges in learning-based NGMA are discussed.
The paper considers the possibility of fine-tuning Llama 2 large language model (LLM) for the disinformation analysis and fake news detection. For fine-tuning, the PEFT/LoRA based approach was used. In the study, the model was fine-tuned for the following tasks: analysing a text on revealing disinformation and propaganda narratives, fact checking, fake news detection, manipulation analytics, extracting named entities with their sentiments. The obtained results show that the fine-tuned Llama 2 model can perform a deep analysis of texts and reveal complex styles and narratives. Extracted sentiments for named entities can be considered as predictive features in supervised machine learning models.
Graded type systems, such as the one underlying the Granule programming language, allow various different properties of a program's behaviour to be tracked via annotating types with additional information, which we call grades. One example of such a property, often used as a case study in prior work on graded types, is information flow control, in which types are graded by a lattice of security levels allowing noninterference properties to be automatically verified and enforced. These typically focus on one particular aspect of security, however, known as confidentiality; public outputs are prohibited from depending on private inputs. Integrity, a property specifying that trusted outputs must not depend on untrusted inputs, has not been examined in this context. This short paper aims to remedy this omission. It is well-known that confidentiality and integrity are in some sense dual properties, but simply reversing the ordering of the security lattice turns out to be unsatisfactory for the purpose of combining both kinds of property in a single system, at least in our setting. We analogize the situation to recent work on embedding both linear and uniqueness types in a graded framework, and use this framing to demonstrate that we can enforce both integrity and confidentiality alongside one another. The main idea is to add an additional flavour of modality annotated for integrity, such that the existing graded comonad for tracking confidentiality now also acts as a relative monad over the new modality, with rules allowing information to flow from trusted to public to private.
The investigation of the similarity between artists and music is crucial in music retrieval and recommendation, and addressing the challenge of the long-tail phenomenon is increasingly important. This paper proposes a Long-Tail Friendly Representation Framework (LTFRF) that utilizes neural networks to model the similarity relationship. Our approach integrates music, user, metadata, and relationship data into a unified metric learning framework, and employs a meta-consistency relationship as a regular term to introduce the Multi-Relationship Loss. Compared to the Graph Neural Network (GNN), our proposed framework improves the representation performance in long-tail scenarios, which are characterized by sparse relationships between artists and music. We conduct experiments and analysis on the AllMusic dataset, and the results demonstrate that our framework provides a favorable generalization of artist and music representation. Specifically, on similar artist/music recommendation tasks, the LTFRF outperforms the baseline by 9.69%/19.42% in Hit Ratio@10, and in long-tail cases, the framework achieves 11.05%/14.14% higher than the baseline in Consistent@10.
Autonomic computing investigates how systems can achieve (user) specified control outcomes on their own, without the intervention of a human operator. Autonomic computing fundamentals have been substantially influenced by those of control theory for closed and open-loop systems. In practice, complex systems may exhibit a number of concurrent and inter-dependent control loops. Despite research into autonomic models for managing computer resources, ranging from individual resources (e.g., web servers) to a resource ensemble (e.g., multiple resources within a data center), research into integrating Artificial Intelligence (AI) and Machine Learning (ML) to improve resource autonomy and performance at scale continues to be a fundamental challenge. The integration of AI/ML to achieve such autonomic and self-management of systems can be achieved at different levels of granularity, from full to human-in-the-loop automation. In this article, leading academics, researchers, practitioners, engineers, and scientists in the fields of cloud computing, AI/ML, and quantum computing join to discuss current research and potential future directions for these fields. Further, we discuss challenges and opportunities for leveraging AI and ML in next generation computing for emerging computing paradigms, including cloud, fog, edge, serverless and quantum computing environments.
We address the task of automatically scoring the competency of candidates based on textual features, from the automatic speech recognition (ASR) transcriptions in the asynchronous video job interview (AVI). The key challenge is how to construct the dependency relation between questions and answers, and conduct the semantic level interaction for each question-answer (QA) pair. However, most of the recent studies in AVI focus on how to represent questions and answers better, but ignore the dependency information and interaction between them, which is critical for QA evaluation. In this work, we propose a Hierarchical Reasoning Graph Neural Network (HRGNN) for the automatic assessment of question-answer pairs. Specifically, we construct a sentence-level relational graph neural network to capture the dependency information of sentences in or between the question and the answer. Based on these graphs, we employ a semantic-level reasoning graph attention network to model the interaction states of the current QA session. Finally, we propose a gated recurrent unit encoder to represent the temporal question-answer pairs for the final prediction. Empirical results conducted on CHNAT (a real-world dataset) validate that our proposed model significantly outperforms text-matching based benchmark models. Ablation studies and experimental results with 10 random seeds also show the effectiveness and stability of our models.
Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification results.
Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this work, we aim to improve the cross-domain robustness of object detection. We tackle the domain shift on two levels: 1) the image-level shift, such as image style, illumination, etc, and 2) the instance-level shift, such as object appearance, size, etc. We build our approach based on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy. The two domain adaptation components are based on H-divergence theory, and are implemented by learning a domain classifier in adversarial training manner. The domain classifiers on different levels are further reinforced with a consistency regularization to learn a domain-invariant region proposal network (RPN) in the Faster R-CNN model. We evaluate our newly proposed approach using multiple datasets including Cityscapes, KITTI, SIM10K, etc. The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191