The remarkable success of transformers in the field of natural language processing has sparked the interest of the speech-processing community, leading to an exploration of their potential for modeling long-range dependencies within speech sequences. Recently, transformers have gained prominence across various speech-related domains, including automatic speech recognition, speech synthesis, speech translation, speech para-linguistics, speech enhancement, spoken dialogue systems, and numerous multimodal applications. In this paper, we present a comprehensive survey that aims to bridge research studies from diverse subfields within speech technology. By consolidating findings from across the speech technology landscape, we provide a valuable resource for researchers interested in harnessing the power of transformers to advance the field. We identify the challenges encountered by transformers in speech processing while also offering insights into potential solutions to address these issues.

Developing interpretable machine learning models has become an increasingly important issue. One way in which data scientists have been able to develop interpretable models has been to use dimension reduction techniques. In this paper, we examine several dimension reduction techniques including two recent approaches developed in the network psychometrics literature called exploratory graph analysis (EGA) and unique variable analysis (UVA). We compared EGA and UVA with two other dimension reduction techniques common in the machine learning literature (principal component analysis and independent component analysis) as well as no reduction to the variables real data. We show that EGA and UVA perform as well as the other reduction techniques or no reduction. Consistent with previous literature, we show that dimension reduction can decrease, increase, or provide the same accuracy as no reduction of variables. Our tentative results find that dimension reduction tends to lead to better performance when used for classification tasks.

Sign Language Translation (SLT) is a promising technology to bridge the communication gap between the deaf and the hearing people. Recently, researchers have adopted Neural Machine Translation (NMT) methods, which usually require large-scale corpus for training, to achieve SLT. However, the publicly available SLT corpus is very limited, which causes the collapse of the token representations and the inaccuracy of the generated tokens. To alleviate this issue, we propose ConSLT, a novel token-level \textbf{Con}trastive learning framework for \textbf{S}ign \textbf{L}anguage \textbf{T}ranslation , which learns effective token representations by incorporating token-level contrastive learning into the SLT decoding process. Concretely, ConSLT treats each token and its counterpart generated by different dropout masks as positive pairs during decoding, and then randomly samples $K$ tokens in the vocabulary that are not in the current sentence to construct negative examples. We conduct comprehensive experiments on two benchmarks (PHOENIX14T and CSL-Daily) for both end-to-end and cascaded settings. The experimental results demonstrate that ConSLT can achieve better translation quality than the strong baselines.

As ChatGPT goes viral, generative AI (AIGC, a.k.a AI-generated content) has made headlines everywhere because of its ability to analyze and create text, images, and beyond. With such overwhelming media coverage, it is almost impossible for us to miss the opportunity to glimpse AIGC from a certain angle. In the era of AI transitioning from pure analysis to creation, it is worth noting that ChatGPT, with its most recent language model GPT-4, is just a tool out of numerous AIGC tasks. Impressed by the capability of the ChatGPT, many people are wondering about its limits: can GPT-5 (or other future GPT variants) help ChatGPT unify all AIGC tasks for diversified content creation? Toward answering this question, a comprehensive review of existing AIGC tasks is needed. As such, our work comes to fill this gap promptly by offering a first look at AIGC, ranging from its techniques to applications. Modern generative AI relies on various technical foundations, ranging from model architecture and self-supervised pretraining to generative modeling methods (like GAN and diffusion models). After introducing the fundamental techniques, this work focuses on the technological development of various AIGC tasks based on their output type, including text, images, videos, 3D content, etc., which depicts the full potential of ChatGPT's future. Moreover, we summarize their significant applications in some mainstream industries, such as education and creativity content. Finally, we discuss the challenges currently faced and present an outlook on how generative AI might evolve in the near future.

With the development of deep learning, advanced dialogue generation methods usually require a greater amount of computational resources. One promising approach to obtaining a high-performance and lightweight model is knowledge distillation, which relies heavily on the pre-trained powerful teacher. Collaborative learning, also known as online knowledge distillation, is an effective way to conduct one-stage group distillation in the absence of a well-trained large teacher model. However, previous work has a severe branch homogeneity problem due to the same training objective and the independent identical training sets. To alleviate this problem, we consider the dialogue attributes in the training of network branches. Each branch learns the attribute-related features based on the selected subset. Furthermore, we propose a dual group-based knowledge distillation method, consisting of positive distillation and negative distillation, to further diversify the features of different branches in a steadily and interpretable way. The proposed approach significantly improves branch heterogeneity and outperforms state-of-the-art collaborative learning methods on two widely used open-domain dialogue datasets.

In recent years, the development of quantum annealers has enabled experimental demonstrations and has increased research interest in applications of quantum annealing, such as in quantum machine learning and in particular for the popular quantum SVM. Several versions of the quantum SVM have been proposed, and quantum annealing has been shown to be effective in them. Extensions to multiclass problems have also been made, which consist of an ensemble of multiple binary classifiers. This work proposes a novel quantum SVM formulation for direct multiclass classification based on quantum annealing, called Quantum Multiclass SVM (QMSVM). The multiclass classification problem is formulated as a single Quadratic Unconstrained Binary Optimization (QUBO) problem solved with quantum annealing. The main objective of this work is to evaluate the feasibility, accuracy, and time performance of this approach. Experiments have been performed on the D-Wave Advantage quantum annealer for a classification problem on remote sensing data. The results indicate that, despite the memory demands of the quantum annealer, QMSVM can achieve accuracy that is comparable to standard SVM methods and, more importantly, it scales much more efficiently with the number of training examples, resulting in nearly constant time. This work shows an approach for bringing together classical and quantum computation, solving practical problems in remote sensing with current hardware.

ChatGPT is a publicly available chatbot that can quickly generate texts on given topics, but it is unknown whether the chatbot is really superior to human writers in all aspects of writing and whether its writing quality can be prominently improved on the basis of updating commands. Consequently, this study compared the writing performance on a narrative topic by ChatGPT and Chinese intermediate English (CIE) learners so as to reveal the chatbot's advantage and disadvantage in writing. The data were analyzed in terms of five discourse components using Coh-Metrix (a special instrument for analyzing language discourses), and the results revealed that ChatGPT performed better than human writers in narrativity, word concreteness, and referential cohesion, but worse in syntactic simplicity and deep cohesion in its initial version. After more revision commands were updated, while the resulting version was facilitated in syntactic simplicity, yet it is still lagged far behind CIE learners' writing in deep cohesion. In addition, the correlation analysis of the discourse components suggests that narrativity was correlated with referential cohesion in both ChatGPT and human writers, but the correlations varied within each group.

We introduce algebraic machine reasoning, a new reasoning framework that is well-suited for abstract reasoning. Effectively, algebraic machine reasoning reduces the difficult process of novel problem-solving to routine algebraic computation. The fundamental algebraic objects of interest are the ideals of some suitably initialized polynomial ring. We shall explain how solving Raven's Progressive Matrices (RPMs) can be realized as computational problems in algebra, which combine various well-known algebraic subroutines that include: Computing the Gr\"obner basis of an ideal, checking for ideal containment, etc. Crucially, the additional algebraic structure satisfied by ideals allows for more operations on ideals beyond set-theoretic operations. Our algebraic machine reasoning framework is not only able to select the correct answer from a given answer set, but also able to generate the correct answer with only the question matrix given. Experiments on the I-RAVEN dataset yield an overall $93.2\%$ accuracy, which significantly outperforms the current state-of-the-art accuracy of $77.0\%$ and exceeds human performance at $84.4\%$ accuracy.

Not long before his death in 2007, my father told me that he "thought he might have" coined the term information technology. It turns out he was right. In an article titled "Management in the 1980's," published in the November, 1958, issue of the Harvard Business Review, Harold J. Leavitt and his co-author, Thomas L. Whisler, identify a "new technology" that "has begun to take hold in American business, one so new that its significance is still difficult to evaluate." Since this technology "does not yet have a single established name," the article notes, "we shall call it information technology. It is composed of several related parts": "techniques for processing large amounts of information rapidly"; "the application of statistical and mathematical methods to decision-making problems"; and "in the offing, though its applications have not yet emerged very clearly . . . the simulation of higher-order thinking through computer programs." By the end of his life, my father had adopted a far more skeptical attitude toward the organizations he earned his living trying to understand and improve.

Drexel University has recently launched a new Artificial Intelligence and Machine Learning (AI/ML) learning group. This initiative is designed to help students, faculty, and staff gain the skills necessary to develop AI/ML applications for research and industry. The goal of this program is to create an environment where people can come together to learn about the latest advancements in AI/ML technology while also gaining hands-on experience with real-world projects. The Drexel AI/ML learning group will be led by Dr. Yaser Abu-Mostafa, Professor of Electrical Engineering at Caltech, who brings decades of experience in machine learning research and teaching. He will be joined by other experts from academia as well as industry professionals who have expertise in various aspects of artificial intelligence and machine learning development.