检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

305 篇 会议
98 篇 期刊文献

馆藏范围

403 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

240 篇 工学
- 167 篇 计算机科学与技术...
- 156 篇 软件工程
- 59 篇 信息与通信工程
- 31 篇 生物工程
- 22 篇 电子科学与技术（可...
- 21 篇 电气工程
- 21 篇 控制科学与工程
- 18 篇 光学工程
- 17 篇 生物医学工程（可授...
- 12 篇 仪器科学与技术
- 12 篇 化学工程与技术
- 8 篇 机械工程
- 5 篇 动力工程及工程热...
- 4 篇 材料科学与工程（可...
- 3 篇 力学（可授工学、理...
- 3 篇 土木工程
137 篇 理学
- 68 篇 物理学
- 61 篇 数学
- 34 篇 生物学
- 20 篇 统计学（可授理学、...
- 12 篇 化学
- 9 篇 系统科学
59 篇 管理学
- 39 篇 图书情报与档案管...
- 22 篇 管理科学与工程(可...
- 6 篇 工商管理
21 篇 法学
- 19 篇 社会学
9 篇 医学
- 7 篇 临床医学
- 4 篇 基础医学(可授医学...
- 4 篇 药学(可授医学、理...
7 篇 文学
- 7 篇 中国语言文学
2 篇 农学
1 篇 经济学
1 篇 教育学

主题

26 篇 semantics
23 篇 feature extracti...
20 篇 training
19 篇 acoustics
16 篇 speech
16 篇 speech processin...
16 篇 speech enhanceme...
15 篇 signal processin...
12 篇 semantic segment...
12 篇 speech recogniti...
10 篇 task analysis
10 篇 speech synthesis
9 篇 ultrasonic imagi...
8 篇 production
8 篇 visualization
8 篇 embeddings
8 篇 robustness
8 篇 ontology
7 篇 electroencephalo...
7 篇 neural networks

机构

140 篇 tianjin key labo...
84 篇 tianjin key labo...
75 篇 college of intel...
73 篇 school of comput...
66 篇 tianjin key labo...
44 篇 tianjin key labo...
29 篇 japan advanced i...
25 篇 school of comput...
22 篇 tianjin key labo...
11 篇 information and ...
10 篇 shenzhen institu...
10 篇 school of new me...
10 篇 school of comput...
10 篇 japan advanced i...
9 篇 tianjin internat...
9 篇 school of future...
8 篇 department of el...
8 篇 college of intel...
7 篇 huiyan technolog...
7 篇 tianjin universi...

作者

68 篇 jianwu dang
57 篇 wang longbiao
56 篇 dang jianwu
44 篇 feng zhiyong
43 篇 longbiao wang
35 篇 zhang xiaowang
23 篇 mei yu
23 篇 ge meng
21 篇 yu mei
21 篇 xuewei li
18 篇 ruiguo yu
17 篇 wang xin
15 篇 zhiyong feng
14 篇 yu ruiguo
14 篇 li xuewei
13 篇 jie gao
13 篇 meng ge
12 篇 mankun zhao
12 篇 gao jie
12 篇 yu jian

语言

398 篇 英文
3 篇 其他
2 篇 中文

检索条件"机构=Tianjin Key Lab Cognitive Computing and Application"

共 403 条记录，以下是11-20 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Continuous Relational Diffusion driven Topic Model with Multi-grained Text for Microblog 30

Continuous Relational Diffusion driven Topic Model with Mult...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Wu, Chenhao He, Ruifang Liu, Chang Wang, Bo School of New Media and Communication Tianjin University Tianjin China College of Intelligence and Computing Tianjin University Tianjin China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China

ISBN: (纸本)9782493814104

Topic model is a statistical model that leverages unsupervised learning to mine hidden topics in document collections. The data sparsity and colloquialism of social texts make it difficult to accurately mine the topics. Traditional methods assume that there are only 0/1-state relationships between the two parties in the social networks, but the relationship status in real life is more complicated, such as continuously changing relationships with different degrees of intimacy. This paper proposes a continuous relational diffusion driven topic model (CRTM) with multi-grained text for Microblog to realize the continuous representation of the relationship state and make up for the context and structural information lost by previous representation methods. Multi-grained text representation learning distinguishes the impact of formal and informal expression on the topics further and alleviates colloquialism problems. Specifically, based on the original social network, the reconstructed social network with continuous relationship status is obtained by using information diffusion technology. The graph convolution model is utilized to learn node embeddings through the new social network. Finally, the neural variational inference is applied to generate topics according to continuous relationships. We validate CRTM on three real datasets, and the experimental results show the effectiveness of the scheme. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Task-Adaptive Generative Adversarial Network Based Speech Dereverberation for Robust Speech Recognition 1

引用

18th National Conference on Man-Machine Speech Communication, NCMMSC 2023

作者： Liu, Ji Li, Nan Ge, Meng Fu, Yanjie Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Japan Advanced Institute of Science and Technology Ishikawa Nomi Japan

ISBN: (数字)9789819706013

ISBN: (纸本)9789819706006

Reverberation is known to severely affect speech recognition performance when speech is recorded in an enclosed space. Deep learning-based speech dereverberation has been remarkably successful in recent years, achieving superior recognition performance for far-field speech applications. However, the output from conventional dereverberation systems cannot be guaranteed suitable for back-end recognition systems because of their different task goals. To bridge the gap between the front-end dereverberation and the back-end recognition, we propose a novel task-adaptive speech dereverberation generative adversarial network (GAN) based speech dereverberation model called Task-adaptive GAN. Specifically, we propose to replace the binary-valued discriminator in a regular generative adversarial network with a novel senone-predicted discriminator, and also introduce a well-designed recognition-aware generator as a dereverberation system. By doing so, the corresponding output distribution will be more suitable for the recognition task. Experimental results on the REVERB corpus show that our proposed approach achieves a relative 18.6% and 8.6% word error rate reduction than the traditional GAN-based baseline system on the simulated set and real set, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Time-Graph Frequency Representation with Singular Value Decomposition for Neural Speech Enhancement

Time-Graph Frequency Representation with Singular Value Deco...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Tingting Wang, Tianrui Ge, Meng Zhang, Qiquan Ge, Zirui Yang, Zhen Nanjing University of Posts and Telecommunications Nanjing China Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China The University of New South Wales Sydney Australia

ISBN: (纸本)9798350368741

Time-frequency (T-F) domain methods for monaural speech enhancement have benefited from the success of deep learning. Recently, focus has been put on designing two-stream network models to predict amplitude mask and phase separately, or, coupling the amplitude and phase into Cartesian coordinates and constructing real and imaginary pairs. However, most methods suffer from the alignment modeling of amplitude and phase (real and imaginary pairs) in a two-stream network framework, which inevitably incurs performance restrictions. In this paper, we introduce a graph Fourier transform defined with the singular value decomposition (GFT-SVD), resulting in real-valued time-graph representation for neural speech enhancement. This real-valued representation-based GFT-SVD provides an ability to align the modeling of amplitude and phase, leading to avoiding recovering the target speech phase information. Our findings demonstrate the effects of real-valued time-graph representation based on GFT-SVD for neutral speech enhancement. The extensive speech enhancement experiments establish that the combination of GFT-SVD and DNN outperforms the combination of GFT with the eigenvector decomposition (GFT-EVD) and magnitude estimation UNet, and outperforms the short-time Fourier transform (STFT) and DNN, regarding objective intelligibility and perceptual quality. We release our source code at: https://***/Wangfighting0015/GFT_project. © 2025 IEEE.

关键词： graph Fourier transform singular value decomposition spectral mapping speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Noise-Disentanglement Metric Learning for Robust Speaker Verification 48

Noise-Disentanglement Metric Learning for Robust Speaker Ver...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Sun, Yao Zhang, Hanyi Wang, Longbiao Lee, Kong Aik Liu, Meng Dang, Jianwu Tianjin University Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin China A*STAR Institute for Infocomm Research Singapore

ISBN: (纸本)9781728163277

Automatic speaker verification (ASV) suffers from performance degradation in noisy environments. To solve this problem, we propose the noise-disentanglement metric learning to reduce the speaker-irrelevant noisy components and build a noise-invariant embedding space. Specifically, the disentanglement module, including the speaker encoder and re-construction module, is dedicated to decoupling speech signals. The speaker encoder is used to disentangle speaker-related components, and the reconstruction module increases the model's ability to constrain the noise information by re-constructing the signal. In addition, distribution optimization is introduced to supervise the spatial structure of speaker embeddings under noisy environments. Experiments on Vox-Celeb1 indicate that the proposed method improves the performance of the speaker verification system in both clean and noisy conditions. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Enhancing Multimodal Alignment with Momentum Augmentation for Dense Video Captioning 48

Enhancing Multimodal Alignment with Momentum Augmentation fo...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wei, Yiwei Yuan, Shaozu Chen, Meng Wang, Longbiao Tianjin University College of Intelligence and Computing Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China Jd Ai Research Beijing China

ISBN: (纸本)9781728163277

Dense video captioning aims to localize multiple events from an untrimmed video and generate corresponding captions for each event. Fusing different modalities(e.g. rgb, flow, audio) via transformer structure is a promising way to improve the caption performance. However, it is challenging for the cross-modal encoder to learn multimodal interactions due to their inherent disparities of distribution. In this paper, we propose a novel transformer structure with contrastive learning to align different modalities. Specifically, to avoid the limitation of small batch size and false contrastive targets, we design an event-aligned momentum augmentation strategy to apply contrast learning for dense video captioning. The experimental result shows that our proposals outperform all existing multimodal fusion methods for dense video captioning. © 2023 IEEE.

关键词： Contrastive learning Dense video captioning Momentum augmentation Multimodal fusion

来源：评论

学校读者我要写书评

暂无评论

Leveraging Positional-Related Local-Global Dependency for Synthetic Speech Detection 48

Leveraging Positional-Related Local-Global Dependency for Sy...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Liu, Xiaohui Liu, Meng Wang, Longbiao Lee, Kong Aik Zhang, Hanyi Dang, Jianwu Tianjin University Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin China Institute for Infocomm Research A*STAR Singapore

ISBN: (纸本)9781728163277

Automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. As synthetic speech exhibits local and global artifacts compared to natural speech, incorporating local-global dependency would lead to better anti-spoofing performance. To this end, we propose the Rawformer that leverages positional-related local-global dependency for synthetic speech detection. The two-dimensional convolution and Transformer are used in our method to capture local and global dependency, respectively. Specifically, we design a novel positional aggregator that integrates local-global dependency by adding positional information and flattening strategy with less information loss. Furthermore, we propose the squeeze-and-excitation Rawformer (SE-Rawformer), which introduces squeeze-and-excitation operation to acquire local dependency better. The results demonstrate that our proposed SE-Rawformer leads to 37% relative improvement compared to the single state-of-the-art system on ASVspoof 2019 LA and generalizes well on ASVspoof 2021 LA. Especially, using the positional aggregator in the SE-Rawformer brings a 43% improvement on average. © 2023 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

VF-Taco2: Towards Fast and Lightweight Synthesis for Autoregressive Models with Variation Autoencoder and Feature Distillation 48

VF-Taco2: Towards Fast and Lightweight Synthesis for Autoreg...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Liu, Yuhao Gong, Cheng Wang, Longbiao Wu, Xixin Liu, Qiuyu Dang, Jianwu Tianjin University College of Intelligence and Computing Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China The Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781728163277

With the development of deep learning, end-to-end neural text-to-speech (TTS) systems have achieved significant improvements in high-quality speech synthesis. However, most of these systems are attention-based autoregressive models, resulting in slow synthesis speed and large model parameter sizes. In this paper, we propose a new fast and lightweight TTS framework named VF-Taco2, which can quickly synthesize speech without GPUs. We first profiled the complexity of decoder process in the current autoregressive model and designed a novel multiple frames prediction module based on variational autoencoder (VAE) to alleviate quality degradation when a larger "reduction factor"is applied. Besides, feature distillation is leveraged to compress a relatively large proposed model to its small version with a minor loss of speech quality. Compared to the original Tacotron 2, our VF-Taco2 achieves a 3.6x-4.4x Mel-spectrum generation acceleration on different performance CPUs, and the parameters are compressed by 1.5x with speech quality maintained. © 2023 IEEE.

关键词： fast knowledge distillation lightweight Speech synthesis VAE

来源：评论

学校读者我要写书评

暂无评论

Time-Domain Speech Enhancement Assisted by Multi-Resolution Frequency Encoder and Decoder 48

Time-Domain Speech Enhancement Assisted by Multi-Resolution ...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Shi, Hao Mimura, Masato Wang, Longbiao Dang, Jianwu Kawahara, Tatsuya Kyoto University Graduate School of Informatics Kyoto Japan Tianjin University College of Intelligence and Computing Tianjin Key Laboratory of Cognitive Computing and Application Tianjin China

ISBN: (纸本)9781728163277

Time-domain speech enhancement (SE) has recently been intensively investigated. Among recent works, DEMUCS [1] introduces multi-resolution STFT loss to enhance performance. However, some resolutions used for STFT contain non-stationary signals, and it is challenging to learn multi-resolution frequency losses simultaneously with only one output. For better use of multi-resolution frequency information, we supplement multiple spectrograms in different frame lengths into the time-domain encoders. They extract stationary frequency information in both narrowband and wideband. We also adopt multiple decoder outputs, each of which computes its corresponding resolution frequency loss. Experimental results show that (1) it is more effective to fuse stationary frequency features than non-stationary features in the encoder, and (2) the multiple outputs consistent with the frequency loss improve performance. Experiments on the Voice-Bank dataset show that the proposed method obtained a 0.14 PESQ improvement. © 2023 IEEE.

关键词： multiresolution spectrograms Speech enhancement time domain

来源：评论

学校读者我要写书评

暂无评论

Class Semantic Prompts Enhanced Prototypical Fusion Method for Few-shot Named Entity Recognition

Class Semantic Prompts Enhanced Prototypical Fusion Method f...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yu, Mei Tao, Yuang Zhao, Mankun Xu, Tianyi Meng, Zechen Zhang, Wenbin Yu, Jian School of Future Technology Tianjin University Tianjin300350 China College of Intelligence and Computing Tianjin University Tianjin300350 China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin300350 China Tianjin Key Laboratory of Advanced Networking Tianjin300350 China Information and Network Center Tianjin University Tianjin300350 China

ISBN: (纸本)9798350368741

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. © 2025 IEEE.

关键词： class semantic few-shot NER prompt learning prototype

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

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

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

ISBN: (纸本)9798350368741

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. © 2025 IEEE.

关键词： large language model multi-label intent detection prompt learning spoken language understanding

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共41页 << < 1 2 3 4 5 6 7 8 9 10 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：