Enhancing speech signal quality in adverse acoustic environments is a persistent challenge in speech processing. Existing deep learning based enhancement methods often struggle to effectively remove background noise and reverberation in real-world scenarios, hampering listening experiences. To address these challenges, we propose a novel approach that uses pre-trained generative methods to resynthesize clean, anechoic speech from degraded inputs. This study leverages pre-trained vocoder or codec models to synthesize high-quality speech while enhancing robustness in challenging scenarios. Generative methods effectively handle information loss in speech signals, resulting in regenerated speech that has improved fidelity and reduced artifacts. By harnessing the capabilities of pre-trained models, we achieve faithful reproduction of the original speech in adverse conditions. Experimental evaluations on both simulated datasets and realistic samples demonstrate the effectiveness and robustness of our proposed methods. Especially by leveraging codec, we achieve superior subjective scores for both simulated and realistic recordings. The generated speech exhibits enhanced audio quality, reduced background noise, and reverberation. Our findings highlight the potential of pre-trained generative techniques in speech processing, particularly in scenarios where traditional methods falter. Demos are available at //whmrtm.github.io/SoundResynthesis.
相關內容
We study a mutually enriching connection between response time analysis in real-time systems and the mixing set problem. Thereby generalizing over known results we present a new approach to the computation of response times in fixed-priority uniprocessor real-time scheduling. We even allow that the tasks are delayed by some period-constrained release jitter. By studying a dual problem formulation of the decision problem as an integer linear program we show that worst-case response times can be computed by algorithmically exploiting a conditional reduction to an instance of the mixing set problem. In the important case of harmonic periods our new technique admits a near-quadratic algorithm to the exact computation of worst-case response times. We show that generally, a smaller utilization leads to more efficient algorithms even in fixed-priority scheduling. Worst-case response times can be understood as least fixed points to non-trivial fixed point equations and as such, our approach may also be used to solve suitable fixed point problems. Furthermore, we show that our technique can be reversed to solve the mixing set problem by computing worst-case response times to associated real-time scheduling task systems. Finally, we also apply our optimization technique to solve 4-block integer programs with simple objective functions.
Recommender systems are used to provide relevant suggestions on various matters. Although these systems are a classical research topic, knowledge is still limited regarding the public opinion about these systems. Public opinion is also important because the systems are known to cause various problems. To this end, this paper presents a qualitative analysis of the perceptions of ordinary citizens, civil society groups, businesses, and others on recommender systems in Europe. The dataset examined is based on the answers submitted to a consultation about the Digital Services Act (DSA) recently enacted in the European Union (EU). Therefore, not only does the paper contribute to the pressing question about regulating new technologies and online platforms, but it also reveals insights about the policy-making of the DSA. According to the qualitative results, Europeans have generally negative opinions about recommender systems and the quality of their recommendations. The systems are widely seen to violate privacy and other fundamental rights. According to many Europeans, these also cause various societal problems, including even threats to democracy. Furthermore, existing regulations in the EU are commonly seen to have failed due to a lack of proper enforcement. Numerous suggestions were made by the respondents to the consultation for improving the situation, but only a few of these ended up to the DSA.
Passenger clustering based on trajectory records is essential for transportation operators. However, existing methods cannot easily cluster the passengers due to the hierarchical structure of the passenger trip information, including multiple trips within each passenger and multi-dimensional information about each trip. Furthermore, existing approaches rely on an accurate specification of the clustering number to start. Finally, existing methods do not consider spatial semantic graphs such as geographical proximity and functional similarity between the locations. In this paper, we propose a novel tensor Dirichlet Process Multinomial Mixture model with graphs, which can preserve the hierarchical structure of the multi-dimensional trip information and cluster them in a unified one-step manner with the ability to determine the number of clusters automatically. The spatial graphs are utilized in community detection to link the semantic neighbors. We further propose a tensor version of Collapsed Gibbs Sampling method with a minimum cluster size requirement. A case study based on Hong Kong metro passenger data is conducted to demonstrate the automatic process of cluster amount evolution and better cluster quality measured by within-cluster compactness and cross-cluster separateness. The code is available at //github.com/bonaldli/TensorDPMM-G.
Designing digital artifacts is not a linear, straightforward process. This is particularly true when applying a user-centered design approach, or co-design, with users who are unable to participate in the design process. Although the reduced participation of a particular user group may harm the end result, the literature on solving this issue is sparse. In this article, proxy design is outlined as a method for involving a user group as proxy users to speak on behalf of a group that is difficult to reach. We present a design ethnography spanning three years at a cancer rehabilitation clinic, where digital artifacts were designed to be used collaboratively by nurses and patients. The empirical data were analyzed using content analysis and consisted of 20 observation days at the clinic, six proxy design workshops, 21 telephone consultations between patients and nurses, and log data from the digital artifact. We show that simulated consultations, with nurses roleplaying as proxies for patients ignited and initiated the design process and enabled an efficient in-depth understanding of patients. Moreover, we reveal how proxy design as a method further expanded the design. We illustrate: (1) proxy design as a method for initiating design, (2) proxy design as an embedded element in co-design and (3) six design guidelines that should be considered when engaging in proxy design. The main contribution is the conceptualization of proxy design as a method that can ignite and initiate the co-design process when important users are unreachable, vulnerable or unable to represent themselves in the co-design process. Based on the empirical findings from a design ethnography that involved nurses as proxy users speaking on behalf of patients, the article shows that roleplaying in proxy design is a fitting way of initiating the design process, outlining proxy design as an embedded element of co-design.
Offensive speech detection is a key component of content moderation. However, what is offensive can be highly subjective. This paper investigates how machine and human moderators disagree on what is offensive when it comes to real-world social web political discourse. We show that (1) there is extensive disagreement among the moderators (humans and machines); and (2) human and large-language-model classifiers are unable to predict how other human raters will respond, based on their political leanings. For (1), we conduct a noise audit at an unprecedented scale that combines both machine and human responses. For (2), we introduce a first-of-its-kind dataset of vicarious offense. Our noise audit reveals that moderation outcomes vary wildly across different machine moderators. Our experiments with human moderators suggest that political leanings combined with sensitive issues affect both first-person and vicarious offense. The dataset is available through //github.com/Homan-Lab/voiced.
Solving complicated AI tasks with different domains and modalities is a key step toward artificial general intelligence. While there are abundant AI models available for different domains and modalities, they cannot handle complicated AI tasks. Considering large language models (LLMs) have exhibited exceptional ability in language understanding, generation, interaction, and reasoning, we advocate that LLMs could act as a controller to manage existing AI models to solve complicated AI tasks and language could be a generic interface to empower this. Based on this philosophy, we present HuggingGPT, a framework that leverages LLMs (e.g., ChatGPT) to connect various AI models in machine learning communities (e.g., Hugging Face) to solve AI tasks. Specifically, we use ChatGPT to conduct task planning when receiving a user request, select models according to their function descriptions available in Hugging Face, execute each subtask with the selected AI model, and summarize the response according to the execution results. By leveraging the strong language capability of ChatGPT and abundant AI models in Hugging Face, HuggingGPT is able to cover numerous sophisticated AI tasks in different modalities and domains and achieve impressive results in language, vision, speech, and other challenging tasks, which paves a new way towards artificial general intelligence.
An in-depth understanding of uncertainty is the first step to making effective decisions under uncertainty. Deep/machine learning (ML/DL) has been hugely leveraged to solve complex problems involved with processing high-dimensional data. However, reasoning and quantifying different types of uncertainties to achieve effective decision-making have been much less explored in ML/DL than in other Artificial Intelligence (AI) domains. In particular, belief/evidence theories have been studied in KRR since the 1960s to reason and measure uncertainties to enhance decision-making effectiveness. We found that only a few studies have leveraged the mature uncertainty research in belief/evidence theories in ML/DL to tackle complex problems under different types of uncertainty. In this survey paper, we discuss several popular belief theories and their core ideas dealing with uncertainty causes and types and quantifying them, along with the discussions of their applicability in ML/DL. In addition, we discuss three main approaches that leverage belief theories in Deep Neural Networks (DNNs), including Evidential DNNs, Fuzzy DNNs, and Rough DNNs, in terms of their uncertainty causes, types, and quantification methods along with their applicability in diverse problem domains. Based on our in-depth survey, we discuss insights, lessons learned, limitations of the current state-of-the-art bridging belief theories and ML/DL, and finally, future research directions.
Graph Convolutional Networks (GCNs) have been widely applied in various fields due to their significant power on processing graph-structured data. Typical GCN and its variants work under a homophily assumption (i.e., nodes with same class are prone to connect to each other), while ignoring the heterophily which exists in many real-world networks (i.e., nodes with different classes tend to form edges). Existing methods deal with heterophily by mainly aggregating higher-order neighborhoods or combing the immediate representations, which leads to noise and irrelevant information in the result. But these methods did not change the propagation mechanism which works under homophily assumption (that is a fundamental part of GCNs). This makes it difficult to distinguish the representation of nodes from different classes. To address this problem, in this paper we design a novel propagation mechanism, which can automatically change the propagation and aggregation process according to homophily or heterophily between node pairs. To adaptively learn the propagation process, we introduce two measurements of homophily degree between node pairs, which is learned based on topological and attribute information, respectively. Then we incorporate the learnable homophily degree into the graph convolution framework, which is trained in an end-to-end schema, enabling it to go beyond the assumption of homophily. More importantly, we theoretically prove that our model can constrain the similarity of representations between nodes according to their homophily degree. Experiments on seven real-world datasets demonstrate that this new approach outperforms the state-of-the-art methods under heterophily or low homophily, and gains competitive performance under homophily.
Substantial efforts have been devoted more recently to presenting various methods for object detection in optical remote sensing images. However, the current survey of datasets and deep learning based methods for object detection in optical remote sensing images is not adequate. Moreover, most of the existing datasets have some shortcomings, for example, the numbers of images and object categories are small scale, and the image diversity and variations are insufficient. These limitations greatly affect the development of deep learning based object detection methods. In the paper, we provide a comprehensive review of the recent deep learning based object detection progress in both the computer vision and earth observation communities. Then, we propose a large-scale, publicly available benchmark for object DetectIon in Optical Remote sensing images, which we name as DIOR. The dataset contains 23463 images and 192472 instances, covering 20 object classes. The proposed DIOR dataset 1) is large-scale on the object categories, on the object instance number, and on the total image number; 2) has a large range of object size variations, not only in terms of spatial resolutions, but also in the aspect of inter- and intra-class size variability across objects; 3) holds big variations as the images are obtained with different imaging conditions, weathers, seasons, and image quality; and 4) has high inter-class similarity and intra-class diversity. The proposed benchmark can help the researchers to develop and validate their data-driven methods. Finally, we evaluate several state-of-the-art approaches on our DIOR dataset to establish a baseline for future research.
Many natural language processing tasks solely rely on sparse dependencies between a few tokens in a sentence. Soft attention mechanisms show promising performance in modeling local/global dependencies by soft probabilities between every two tokens, but they are not effective and efficient when applied to long sentences. By contrast, hard attention mechanisms directly select a subset of tokens but are difficult and inefficient to train due to their combinatorial nature. In this paper, we integrate both soft and hard attention into one context fusion model, "reinforced self-attention (ReSA)", for the mutual benefit of each other. In ReSA, a hard attention trims a sequence for a soft self-attention to process, while the soft attention feeds reward signals back to facilitate the training of the hard one. For this purpose, we develop a novel hard attention called "reinforced sequence sampling (RSS)", selecting tokens in parallel and trained via policy gradient. Using two RSS modules, ReSA efficiently extracts the sparse dependencies between each pair of selected tokens. We finally propose an RNN/CNN-free sentence-encoding model, "reinforced self-attention network (ReSAN)", solely based on ReSA. It achieves state-of-the-art performance on both Stanford Natural Language Inference (SNLI) and Sentences Involving Compositional Knowledge (SICK) datasets.
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