检索结果-内蒙古大学图书馆

EDSep: An Effective Diffusion-Based Method for speech Source Separation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Dong, Jinwei Wang, Xinsheng Mao, Qirong School of Computer Science and Communication Engineering Jiangsu University China Jiangsu Engineering Research Center of Big Data Ubiquitous Perception and Intelligent Agriculture Applications China Provincial Key Laboratory of Computational Intelligence and New Technologies in Low-Altitude Digital Agriculture Zhenjiang China Audio Speech and Language Processing Group School of Computer Science Northwestern Polytechnical University Xi’an China

Generative models have attracted considerable attention for speech separation tasks, and among these, diffusion-based methods are being explored. Despite the notable success of diffusion techniques in generation tasks, their adaptation to speech separation has encountered challenges, notably slow convergence and suboptimal separation outcomes. To address these issues and enhance the efficacy of diffusion-based speech separation, we introduce EDSep, a novel single-channel method grounded in score matching via stochastic differential equation (SDE). This method enhances generative modeling for speech source separation by optimizing training and sampling efficiency. Specifically, a novel denoiser function is proposed to approximate data distributions, which obtains ideal denoiser outputs. Additionally, a stochastic sampler is carefully designed to resolve the reverse SDE during the sampling process, gradually separating speech from mixtures. Extensive experiments on databases such as WSJ0-2mix, LRS2-2mix, and VoxCeleb2-2mix demonstrate our proposed method’s superior performance over existing diffusion and discriminative models, validating its efficacy. Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic systems

A Semantics-Aware Normalizing Flow Model for Anomaly Detection

学校读者我要写书评

暂无评论

A Semantics-Aware Normalizing Flow Model for Anomaly Detecti...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Wei Ma Shiyong Lan Weikang Huang Wenwu Wang Hongyu Yang Yitong Ma Yongjie Ma College of Computer Science Sichuan University China National Key Laboratory of Fundamental Science on Synthetic Vision China Center for Vision Speech and Signal Processing University of Surrey UK

Anomaly detection in computer vision aims to detect outliers from input image data. Examples include texture defect detection and semantic discrepancy detection. However, existing methods are limited in detecting both types of anomalies, especially for the latter. In this work, we propose a novel semantics-aware normalizing flow model to address the above challenges. First, we employ the semantic features extracted from a backbone network as the initial input of the normalizing flow model, which learns the mapping from the normal data to a normal distribution according to semantic attributes, thus enhances the discrimination of semantic anomaly detection. Second, we design a new feature fusion module in the normalizing flow model to integrate texture features and semantic features, which can substantially improve the fitting of the distribution function with input data, thus achieving improved performance for the detection of both types of anomalies. Extensive experiments on five well-known datasets for semantic anomaly detection show that the proposed method outperforms the state-of-the-art baselines. The codes will be available at https://***/SYLan2019/SANF-AD.

关键词：

Joint Generative-Contrastive Representation Learning for Anomalous Sound Detection

学校读者我要写书评

暂无评论

Joint Generative-Contrastive Representation Learning for Ano...

International Conference on Acoustics, speech, and Signal processing (ICASSP)

作者： Xiao-Min Zeng Yan Song Zhu Zhuo Yu Zhou Yu-Hong Li Hui Xue Li-Rong Dai Ian McLoughlin National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China Alibaba Group China ICT Cluster Singapore Institute of Technology Singapore

In this paper, we propose a joint generative and contrastive representation learning method (GeCo) for anomalous sound detection (ASD). GeCo exploits a Predictive AutoEncoder (PAE) equipped with self-attention as a generative model to perform frame-level prediction. The output of the PAE together with original normal samples, are used for supervised contrastive representative learning in a multi-task framework. Besides cross-entropy loss between classes, contrastive loss is used to separate PAE output and original samples within each class. GeCo aims to better capture context information among frames, thanks to the self-attention mechanism for PAE model. Furthermore, GeCo combines generative and contrastive learning from which we aim to yield more effective and informative representations, compared to existing methods. Extensive experiments have been conducted on the DCASE2020 Task2 development dataset, showing that GeCo outperforms state-of-the-art generative and discriminative methods.

关键词： Representation learning Self-supervised learning Signal processing Predictive models Multitasking Robustness Acoustics

DLAHSD: Dynamic Label Adopted In Auxiliary Head for SAR Detection

学校读者我要写书评

暂无评论

DLAHSD: Dynamic Label Adopted In Auxiliary Head for SAR Dete...

IEEE International Conference on Image processing

作者： Xiaoxiao Yin Shiyong Lan Weikang Huang Yitong Ma Wenwu Wang Hongyu Yang Yilin Zheng National Key Laboratory of Fundamental Science on Synthetic Vision China College of Computer Science Sichuan University China Center for Vision Speech and Signal Processing University of Surrey UK

Ship detection in synthetic aperture radar (SAR) images is a major issue in maritime surveillance and port management. Existing challenges are mainly as follows: (1) Tiny ships are mixed with scattered noise spots on the sea. (2) Ships are present in extreme aspect-ratios and various scales. (3) The land background blurs the outline of coastal ships. To address these problems, we propose an efficient detection neural network (DLAHSD) that integrates the Multi-scale Feature Location Fusion (MFLF) module and the Auxiliary Detection Head (ADH) based centerNet. In addition, we designed a Dynamic Elliptic Gaussian (DEG) module to label the heatmap of ships. Experimental results on the challenging SSDD dataset show that our model offers improved performance over the baseline methods. The codes will be available at https://***/SYLan2019/DLAHSD.

关键词：

JOINT GENERATIVE-CONTRASTIVE REPRESENTATION LEARNING FOR ANOMALOUS SOUND DETECTION

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zeng, Xiao-Min Song, Yan Zhuo, Zhu Zhou, Yu Li, Yu-Hong Xue, Hui Dai, Li-Rong McLoughlin, Ian National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China ICT Cluster Singapore Institute of Technology Singapore Alibaba Group China

关键词： Germanium alloys

SL-REDU GSL: A Large Greek Sign language Recognition Corpus

学校读者我要写书评

暂无评论

SL-REDU GSL: A Large Greek Sign Language Recognition Corpus

Acoustics, speech, and Signal processing Workshops (ICASSPW), IEEE International Conference on

作者： Katerina Papadimitriou Galini Sapountzaki Kyriaki Vasilaki Eleni Efthimiou Stavroula-Evita Fotinea Gerasimos Potamianos Department of Electrical & Computer Engineering University of Thessaly Volos Greece Department of Special Education University of Thessaly Volos Greece Institute for Language & Speech Processing Athena Research & Innovation Center Athens Greece

We present a large multi-signer video corpus for the Greek Sign language (GSL), suitable for the development and evaluation of GSL recognition algorithms. The database has been collected as part of the “SL-ReDu” project that focuses on the education use-case of systematic teaching of GSL as a second language (L2). The project aims to assist this process by allowing self-monitoring and objective assessment of GSL learners’ productions through the use of recognition technology, thus requiring suitable data resources relevant to the aforementioned use-case. To this end, we present the SL-ReDu GSL corpus, an extensive RGB+D video collection of 21 informants with a duration of 36 hours, recorded under studio conditions, consisting of: (i) isolated signs; (ii) continuous signing (annotated at the sentence level); and (iii) fingerspelling of words. We provide a detailed description of the design and acquisition methods used to develop it, along with corpus statistics and a comparison to existing sign language datasets. The SL-ReDu GSL corpus, as well as proposed frameworks for recognition experiments on it, are publicly available at https://***/corpus.

关键词：

ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension 29

学校读者我要写书评

暂无评论

ET5: A Novel End-to-end Framework for Conversational Machine...

29th International Conference on Computational Linguistics, COLING 2022

作者： Zhang, Xiao Huang, Heyan Chi, Zewen Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology China Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications China Southeast Academy of Information Technology Beijing Institute of Technology China

Conversational machine reading comprehension (CMRC) aims to assist computers to understand an natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text. Existing methods typically require three steps: (1) decision making based on entailment reasoning;(2) span extraction if required by the above decision;(3) question rephrasing based on the extracted span. However, for nearly all these methods, the span extraction and question rephrasing steps cannot fully exploit the fine-grained entailment reasoning information in decision making step because of their relative independence, which will further enlarge the information gap between decision making and question phrasing. Thus, to tackle this problem, we propose a novel end-to-end framework for conversational machine reading comprehension based on shared parameter mechanism, called entailment reasoning T5 (ET5). Despite the lightweight of our proposed framework, experimental results show that the proposed ET5 achieves new state-of-the-art results on the ShARC leaderboard with the BLEU-4 score of 55.2. Our model and code are publicly available © 2022 Proceedings - International Conference on Computational Linguistics, COLING. All rights reserved.

关键词： Decision making

GIFT: Graph-Induced Fine-Tuning for Multi-Party Conversation Understanding

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Gu, Jia-Chen Ling, Zhen-Hua Liu, Quan Liu, Cong Hu, Guoping National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China State Key Laboratory of Cognitive Intelligence China iFLYTEK Research Hefei China

Addressing the issues of who saying what to whom in multi-party conversations (MPCs) has recently attracted a lot of research attention. However, existing methods on MPC understanding typically embed interlocutors and utterances into sequential information flows, or utilize only the superficial of inherent graph structures in MPCs. To this end, we present a plug-and-play and lightweight method named graph-induced fine-tuning (GIFT) which can adapt various Transformer-based pre-trained language models (PLMs) for universal MPC understanding. In detail, the full and equivalent connections among utterances in regular Transformer ignore the sparse but distinctive dependency of an utterance on another in MPCs. To distinguish different relationships between utterances, four types of edges are designed to integrate graph-induced signals into attention mechanisms to refine PLMs originally designed for processing sequential texts. We evaluate GIFT by implementing it into three PLMs, and test the performance on three downstream tasks including addressee recognition, speaker identification and response selection. Experimental results show that GIFT can significantly improve the performance of three PLMs on three downstream tasks and two benchmarks with only 4 additional parameters per encoding layer, achieving new state-of-the-art performance on MPC understanding. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

SHINE: Syntax-augmented Hierarchical Interactive Encoder for Zero-shot Cross-lingual Information Extraction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ma, Jun-Yu Gu, Jia-Chen Ling, Zhen-Hua Liu, Quan Liu, Cong Hu, Guoping National Engineering Research Center of Speech and Language Information Processing University of Science and Technology of China Hefei China State Key Laboratory of Cognitive Intelligence China iFLYTEK Research Hefei China

Zero-shot cross-lingual information extraction (IE) aims at constructing an IE model for some low-resource target languages, given annotations exclusively in some rich-resource languages. Recent studies based on language-universal features have shown their effectiveness and are attracting increasing attention. However, prior work has neither explored the potential of establishing interactions between language-universal features and contextual representations nor incorporated features that can effectively model constituent span attributes and relationships between multiple spans. In this study, a syntax-augmented hierarchical interactive encoder (SHINE) is proposed to transfer cross-lingual IE knowledge. The proposed encoder is capable of interactively capturing complementary information between features and contextual information, to derive language-agnostic representations for various IE tasks. Concretely, a multilevel interaction network is designed to hierarchically interact the complementary information to strengthen domain adaptability. Besides, in addition to the well-studied syntax features of part-of-speech and dependency relation, a new syntax feature of constituency structure is introduced to model the constituent span information which is crucial for IE. Experiments across seven languages on three IE tasks and four benchmarks verify the effectiveness and generalization ability of the proposed method. Copyright © 2023, The Authors. All rights reserved.

关键词： Information retrieval