检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Mei Yu Yuang Tao Mankun Zhao Tianyi Xu Zechen Meng Wenbin Zhang Jian Yu School of Future Technology Tianjin University Tianjin China College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Tianjin Key Laboratory of Advanced Networking Tianjin China Information and Network Center Tianjin University Tianjin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Few-shot named entity recognition is to identify named entities in scenarios where labeled data is scarce. Existing prototype building methods ignore the use of class semantic and it is difficult to obtain accurate prototype representations only by relying on few support samples. In this paper, we propose a class semantic prompts enhanced prototypical fusion method (CSFP). Specifically, we design a class-semantic prototype that adapts to current task through prompts. In order to add intra-class similarity to the existing prototype and obtain a more accurate and stable prototype representation, we consider the samples distribution and fuse class-semantic prototype with existing prototype through a weighted strategy. Experimental results on two few-shot NER benchmarks show that our method outperforms previous SOTA methods. The analysis further verifies the effectiveness of our method.

关键词： Accuracy Fuses Semantics Buildings Prototypes Named entity recognition Signal processing Benchmark testing Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Multi-Granular Multimodal Clue Fusion for Meme Understanding

arXiv

引用

arXiv 2025年

作者： Zheng, Li Fei, Hao Dai, Ting Peng, Zuquan Li, Fei Ma, Huisheng Teng, Chong Ji, Donghong Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China National University of Singapore Singapore Singapore Laboratory for Advanced Computing and Intelligence Engineering Wuxi China North China Institute of Computing Technology Beijing China

With the continuous emergence of various social media platforms frequently used in daily life, the multimodal meme understanding (MMU) task has been garnering increasing attention. MMU aims to explore and comprehend the meanings of memes from various perspectives by performing tasks such as metaphor recognition, sentiment analysis, intention detection, and offensiveness detection. Despite making progress, limitations persist due to the loss of fine-grained metaphorical visual clue and the neglect of multimodal text-image weak correlation. To overcome these limitations, we propose a multi-granular multimodal clue fusion model (MGMCF) to advance MMU. Firstly, we design an object-level semantic mining module to extract object-level image feature clues, achieving fine-grained feature clue extraction and enhancing the model’s ability to capture metaphorical details and semantics. Secondly, we propose a brand-new global-local cross-modal interaction model to address the weak correlation between text and images. This model facilitates effective interaction between global multimodal contextual clues and local unimodal feature clues, strengthening their representations through a bidirectional cross-modal attention mechanism. Finally, we devise a dual-semantic guided training strategy to enhance the model’s understanding and alignment of multimodal representations in the semantic space. Experiments conducted on the widely-used MET-MEME bilingual dataset demonstrate significant improvements over state-of-the-art baselines. Specifically, there is an 8.14% increase in precision for offensiveness detection task, and respective accuracy enhancements of 3.53%, 3.89%, and 3.52% for metaphor recognition, sentiment analysis, and intention detection tasks. These results, underpinned by in-depth analyses, underscore the effectiveness and potential of our approach for advancing MMU. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Prompt Learning Framework with Large Language Model Augmentation for Few-shot Multi-label Intent Detection

A Prompt Learning Framework with Large Language Model Augmen...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ning Zhuang Xiao Wei Junlei Li Xiaobao Wang Chenyang Wang Longbiao Wang Jianwu Dang Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China Huiyan Technology (Tianjin) Co. Ltd Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Intent detection (ID) is essential in spoken language understanding, especially in multi-label settings where intent labels are interdependent and diverse. Existing methods like SE-MLP and QA-FT struggle in few-shot settings, due to limited data availability and efficiency concerns. To address this, we introduce a Prompt Learning framework with large language Model Augmentation (PLMA) for few-shot multi-label ID. In this study, we make three contributions. First, PLMA integrates large language models (LLMs) with small language models (SLMs), using LLMs to enhance SLMs, with prompt learning as the core framework. Second, it leverages LLMs to improve the model’s understanding of both queries and labels by intent spans extraction and answer space expansion. Third, PLMA refines the QA-FT. A novel QA format template is designed to allow single-step training and inference for each input, improving efficiency. Experiments on NLU++ show that PLMA significantly outperforms other baselines in both in-domain and cross-domain settings, demonstrating its effectiveness in combining the strengths of both small and large models.

关键词： Training Adaptation models Accuracy Large language models Signal processing Natural language processing Acoustics Multilingual Speech processing

来源：评论

学校读者我要写书评

暂无评论

Progressive Residual Extraction Based Pre-Training for Speech Representation Learning

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1825-1837页

作者： Tianrui Wang Jin Li Ziyang Ma Rui Cao Xie Chen Longbiao Wang Meng Ge Xiaobao Wang Yuguang Wang Jianwu Dang Nyima Tashi Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China Huiyan Technology (Tianjin) Company Ltd. Tianjin China Saw Swee Hock School of Public Health National University of Singapore Singapore Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China School of Information Science and Technology Tibet University Lhasa China State Key Laboratory of Tibetan Intelligence Lhasa China

Self-supervised learning (SSL) has garnered significant attention in speech processing, particularly excelling in linguistic tasks such as speech recognition. However, improving the performance of pre-trained models across various downstream tasks—each requiring distinct types of speech information—remains a significant challenge. To address this, we propose a progressive residual extraction based SSL method, named ProgRE. Specifically, we introduce two lightweight, specialized task modules into an encoder-style SSL backbone to enhance its ability to extract pitch variation and speaker information from speech. Furthermore, to mitigate the incompatibility between the reinforced pitch variation and speaker information and the learning of content information, we employ residual extraction, leveraging the extracted representations as references or conditioning signals to guide the subsequent modules in more effectively learning content-related information under the supervision of HuBERT-based speech masking prediction. In this manner, we can incrementally extract pitch variation, speaker, and content representations from the input speech. Finally, these multiple representations, each capturing diverse speech information, are combined using different layer weights to produce task-specific representations for various downstream tasks. Experimental results demonstrate that our ProgRE achieves significant performance improvements across several tasks, such as speaker identification, speech recognition, emotion recognition, speech enhancement, and voice conversion, outperforming excellent SSL methods like wav2vec2.0, HuBERT, and WavLM.

关键词： Data mining Feature extraction Transformers Speech recognition Training Speech enhancement Acoustics Vector quantization Self-supervised learning Germanium

来源：评论

学校读者我要写书评

暂无评论

WMRE: Enhancing Distant Supervised Relation Extraction with Word-level Multi-instance Learning and Multi-hierarchical Feature

WMRE: Enhancing Distant Supervised Relation Extraction with ...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Xiang Ying Xiangchuan Xie Tianyi Xu Yue Zhao Zechen Meng Mankun Zhao College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Tianjin Key Laboratory of Advanced Networking Tianjin China School of New Media and Communication Tianjin University Tianjin China Information and Network Center Tianjin University Tianjin China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Distant supervised relation extraction (DSRE) obtains large amounts of data cost-effectively by aligning knowledge base with natural texts but also brings noisy data. Existing methods deal with noise through multi-instance learning (MIL) with attention. However, these approaches typically use attention at sentence-level and above, while ignoring word-level information. Intuitively, words in the same sentence are also of different importance. However, effective methods for distinguishing word-level importance differences are still lacking. Because multiplying with weighted attention leads word embeddings to be shifted in vector space. Therefore, we proposed WMRE. Specifically, WMRE concatenates the embeddings of multiple sentences. Then it uses filtering attention to remove low-importance words at different levels to extract multi-hierarchical features. In WMRE, words are the smallest units of mining information, and filtering attention distinguishes word-level importance differences while avoiding the embedding shifts. Extensive experiments on two widely used datasets show that WMRE fully utilizes word-level information and achieves state-of-the-art (SOTA) on both datasets.

关键词： Filtering Noise Knowledge based systems Feature extraction Vectors Acoustics Data mining Noise measurement Speech processing

来源：评论

学校读者我要写书评

暂无评论

Characteristic-Specific Partial Fine-Tuning for Efficient Emotion and Speaker Adaptation in Codec Language Text-to-Speech Models

arXiv

引用

arXiv 2025年

作者： Wang, Tianrui Ge, Meng Gong, Cheng Qiang, Chunyu Wang, Haoyu Huang, Zikang Jiang, Yu Wang, Xiaobao Chen, Xie Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Guangdong Laboratory of Artificial Intelligence and Digital Economy Guangdong China China Telecom Beijing China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China Co. Ltd Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong China

Recently, emotional speech generation and speaker cloning have garnered significant interest in text-to-speech (TTS). With the open-sourcing of codec language TTS models trained on massive datasets with large-scale parameters, adapting these general pre-trained TTS models to generate speech with specific emotional expressions and target speaker characteristics has become a topic of great attention. Common approaches, such as full and adapter-based fine-tuning, often overlook the specific contributions of model parameters to emotion and speaker control. Treating all parameters uniformly during fine-tuning, especially when the target data has limited content diversity compared to the pre-training corpus, results in slow training speed and an increased risk of catastrophic forgetting. To address these challenges, we propose a characteristic-specific partial fine-tuning strategy, short as CSP-FT. First, we use a weighted-sum approach to analyze the contributions of different Transformer layers in a pre-trained codec language TTS model for emotion and speaker control in the generated speech. We then selectively fine-tune the layers with the highest and lowest characteristic-specific contributions to generate speech with target emotional expression and speaker identity. Experimental results demonstrate that our method achieves performance comparable to, or even surpassing, full fine-tuning in generating speech with specific emotional expressions and speaker identities. Additionally, CSP-FT delivers approximately 2× faster training speeds, fine-tunes only around 8% of parameters, and significantly reduces catastrophic forgetting. Furthermore, we show that codec language TTS models perform competitively with self-supervised models in speaker identification and emotion classification tasks, offering valuable insights for developing universal speech processing models. © 2025, CC BY.

关键词： C (programming language)

来源：评论

学校读者我要写书评

暂无评论

FASTEN: Video Event Localization based on Audio-Visual Feature Alignment and Multi-Scale Temporal Enhancement

引用

IEEE Signal Processing Letters 2025年 32卷 2010-2014页

作者： Liu, Yin Wu, Qin Zeng, Mingyong Liu, Yahan Pan, Yuying Jiangnan University School of Artificial Intelligence and Computer Science Wuxi 214122 China State Key Laboratory of Mathematical Engineering and Advanced Computing Wuxi 214083 China Jiangnan University School of Internet of Things Engineering Wuxi 214122 China

The audio-visual event localization task investigates how audio and visual modalities can mutually enhance video event localization. Current methods often rely on single-modality features or lack effective initial alignment between modalities. Although feature pyramids with multiple resolutions are commonly used, the effective and efficient mining of cross-modal and cross-level semantics remains a challenge. In this letter, we propose FASTEN, which stands for audio-visual Feature Alignment and multi-Scale Temporal ENhancement. Novel features derived from an initially aligned multimodal model are introduced and have been shown to be remarkably beneficial. We design an efficient encoder by sharing weights across all pyramid levels and propose a weighted cross-modal attention module to facilitate interaction between modalities. Additionally, global and local pyramids are fused to jointly capture multi-scale temporal dependencies. Evaluated on UnAV-100 and AVE, our method significantly outperforms competing solutions while reducing parameters and computational FLOPs greatly. © 1994-2012 IEEE.

关键词： Audio-visual event localization cross-modal fusion multi-scale enhancement

来源：评论

学校读者我要写书评

暂无评论

DAT: Dual-branch Adapter-Tuning for Few-shot Recognition

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Chen, Junxi Wu, Guangxing Li, Hongxiang Chen, Jiankang Zhang, Wentao Zheng, Weishi Wang, Ruixuan Sun Yat-sen Univerisity College of Computer Science and Engineering Guangzhou510275 China Peking University School of Electronic and Computer Engineering Shenzhen518055 China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Guangzhou510275 China Sun Yat-sen Univerisity School of Computer Science and Engineering Guangzhou510275 China Peng Cheng Laboratory Shenzhen518066 China

Parameter-Efficient Fine-Tuning methods based on vision-language models (such as CLIP) for few-shot learning have recently received considerable attention. However, previous works only fine-tune either the image or text branch, breaking the alignment of the original two branches, meanwhile fine-tuning both branches of the CLIP would inevitably introduce more trainable parameters and likely cause more severe over-fitting due to the limited training data. In this study, we propose a novel Dual-branch Adapter-Tuning framework (DAT), which collaboratively trains the visual adapter and textual adapter added to the two branches of the original CLIP with multiple consistency constraints. By effectively utilizing the semantically detailed class-specific prompts and outputs of the original CLIP to guide the fine-tuning of both branches, our method gains exceptional adaptation ability to the downstream few-shot learning tasks and alleviates the over-fitting issue, meanwhile maximally preserving the generalization ability of the original CLIP model. Our proposed framework has achieved superior performance on diverse datasets under various few-shot learning settings compared to the existing approaches. The source code is available at https://***/SandyXi/DAT. © 1991-2012 IEEE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

CroPrompt: Cross-task Interactive Prompting for Zero-shot Spoken Language Understanding

CroPrompt: Cross-task Interactive Prompting for Zero-shot Sp...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Libo Qin Fuxuan Wei Qiguang Chen Jingxuan Zhou Shijue Huang Jiasheng Si Wenpeng Lu Wanxiang Che School of Computer Science and Engineering Central South University China Key Laboratory of Data Intelligence and Advanced Computing in Provincial Universities Soochow University China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology China Harbin Institute of Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences)

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Slot filling and intent detection are two highly correlated tasks in spoken language understanding (SLU). Recent SLU research attempts to explore zero-shot prompting techniques in large language models to alleviate the data scarcity problem. Nevertheless, the existing prompting work ignores the cross-task interaction information for SLU, which leads to sub-optimal performance. To solve this problem, we present the pioneering work of Cross-task Interactive Prompting (CroPrompt) for SLU, which enables the model to interactively leverage the information exchange across the correlated tasks in SLU. Additionally, we further introduce a multi-task self-consistency mechanism to mitigate the error propagation caused by the intent information injection. We conduct extensive experiments on the standard SLU benchmark and the results reveal that CroPrompt consistently outperforms the existing prompting approaches. In addition, the multi-task self-consistency mechanism can effectively ease the error propagation issue, thereby enhancing the performance. We hope this work can inspire more research on cross-task prompting for SLU.

关键词： Large language models Signal processing Benchmark testing Multitasking Filling Acoustics Speech processing Information exchange Standards

来源：评论

学校读者我要写书评

暂无评论

Visual Class Incremental Learning with Textual Priors Guidance based on an Adapted Vision-Language Model

引用

IEEE Transactions on Multimedia 2025年

作者： Zhang, Wentao Yu, Tong Wang, Ruixuan Xie, Jianhui Trucco, Emanuele Zheng, Wei-Shi Yang, Xiaobo Sun Yat-sen Univerisity School of Computer Science and Engineering Guangzhou510275 China Peng Cheng Laboratory Shenzhen518066 China MOE Key Laboratory of Machine Intelligence and Advanced Computing Guangzhou510275 China Second Affiliated Hospital Guangzhou University of Chinese Medicine State Key Laboratory of Dampness Syndrome of Chinese Medicine Guangzhou510260 China Guangdong Provincial Key Laboratory of Clinical Research on Traditional Chinese Medicine Syndrome Guangzhou510120 China University of Dundee School of Science and Engineering DundeeDD1 4HN United Kingdom

An ideal artificial intelligence (AI) system should have the capability to continually learn like humans. However, when learning new knowledge, AI systems often suffer from catastrophic forgetting of old knowledge. Although many continual learning methods have been proposed, they often ignore the issue of misclassifying similar classes and make insufficient use of textual priors of visual classes to improve continual learning performance. In this study, we propose a continual learning framework based on a pre-trained vision-language model (VLM) that does not require storing old class data. This framework utilizes parameter-efficient fine-tuning of the VLM's text encoder for constructing a shared and consistent semantic textual space throughout the continual learning process. The textual priors of visual classes are encoded by the adapted VLM's text encoder to generate discriminative semantic representations, which are then used to guide the learning of visual classes. Additionally, fake out-of-distribution (OOD) images constructed from each training image further assist in the learning of visual classes. Extensive empirical evaluations on three natural datasets and one medical dataset demonstrate the superiority of the proposed framework. The source code is available at https://***/OpenMedIA/CIL_Adapterd_VLM. © 1999-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：