检索结果-内蒙古大学图书馆

Subspace Gaussian Mixture Modeling for low-resource non-native Punjabi Language Speech Recognition

Procedia computer science 2025年 259卷 408-415页

作者： Puneet Bawa Virender Kadyan Gunjan Chhabra Ashish Chopra Centre of Excellence for Speech and Multimodal Laboratory Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Machine Intelligence Research Centre School of Computer Science UPES Energy Acres Bidholi Dehradun-248007 Uttarakhand India Department of CSE Graphic Era Hill University； Graphic Era Deemed to be University Dehradun Uttarakhand-248007 Department of Computer Science and Applications Seth Jai Parkash Mukand Lal Institute of Engineering and Technology Radaur Haryana

The advancement of non-native recognition of speech is becoming more significant as individual research interest in communicating with various languages has developed. However, because of the limited ability to include semantic level contextual signals for non-native language, the resilience and performance of Automatic Speech Recognition (ASR) systems have been degraded. The objectives of this research include the collection and pre-processing of speech data, the training of an acoustic model using Gaussian Mixture Models (GMMs), the development of a Punjabi-specific language model, and the creation of a comprehensive pronunciation dictionary. Similarly, the performance of proposed ASR system has been evaluated using relevant measures that consider the unique characteristics of excellent non-native Punjabi speakers’ speech. Furthermore, three three distinct kinds of language models using a combined subspace Gaussian Mixture Modeling and Hidden Markov Modeling (sGMM-HMM) technique has been employed with an objective of tackling the issue of shared-state parameters due to a limited dataset. Overall, the findings obtained on sGMM-HMM yielded a Word Error Rate (WER) of 16.41%, which appears respectable in contrast to the native language ASR system.

关键词： Non-Native Speech Recognition Acoustic Modeling Gaussian Mixture Modeling Punjabi Speech Recognition

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Based Method for Structuring the Chinese Pathological Reports of Lung Specimen 11

A Deep Learning Based Method for Structuring the Chinese Pat...

引用

11th International Conference on Information science and Technology, ICIST 2021

作者： Lan, Tianzhong Li, Jingwei Xu, Xiuyuan Wang, Chengdi Yi, Zhang Li, Weimin Guo, Jixiang Sichuan University Machine Intelligence Laboratory School of Computer Science Chengdu China Sichuan University Department of Respiratory and Critical Care Medicine West China Hospital Chengdu China

ISBN: (纸本)9781665412667

As a kind of electronic reports in text form, the Chinese pathology report of lung specimen contains a large amount of information that is important for clinicians to further analysis and mining. However, various expressions and no fixed format increases the difficulty of extracting and standardizing this information. In this paper, we focus on the extraction of lung lesion locations and the corresponding diagnosis from these reports. And to overcome the difficulties, a structured processing method based on deep learning and the idea of part-of-speech (POS) tagging was proposed. Firstly, the data of lung pathology specimen reports are preprocessed to normalize the medical terms. Secondly, the bidirectional Long Short-Term Memory (Bi-LSTM) neural network is adopted to extract the information of lesion locations and pathological diagnosis from each report. Finally, the obtained information is screened by an information filter method to generate the final structured results. Experimental results on the self-constructed datasets indicated that the proposed method can be beneficial for structuring pathology reports of lung specimen and obtained state-of-the-art results. © 2021 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Audio Captioning Using Soft and Hard Prompts

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2045-2058页

作者： Yiming Zhang Xuenan Xu Ruoyi Du Haohe Liu Yuan Dong Zheng-Hua Tan Wenwu Wang Zhanyu Ma Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Centre for Vision Speech and Signal Processing University of Surrey Guildford U.K. Department of Electronic Systems Aalborg University Aalborg Denmark

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test set from the same dataset. Such methods have two limitations. First, these methods are often data-hungry and require time-consuming and expensive human annotations to obtain audio-text pairs. Second, these models often suffer from performance degradation in cross-domain scenarios, i.e., when the input audio comes from a different domain than the training set, and this issue has received little attention. To address these issues, we propose a new zero-shot method for audio captioning. Our method is built on the contrastive language-audio pre-training (CLAP) model. During training, the model reconstructs the ground-truth caption using the CLAP text encoder. In the inference stage, the model generates text descriptions from the CLAP audio embeddings of given audio inputs. To enhance the ability of the model in transitioning from text-to-text generation to audio-to-text generation, we propose to use the mixed-augmentations-based soft prompt to learn more robust latent representations, leveraging instance replacement and embedding augmentation. Additionally, we introduce the retrieval-based acoustic-aware hard prompt to improve the cross-domain performance of the model by employing the domain-agnostic label information of sound events. Extensive experiments on AudioCaps and Clotho benchmarks show the effectiveness of our proposed method, which outperforms other zero-shot audio captioning approaches for in-domain scenarios and outperforms the compared methods for cross-domain scenarios, underscoring the generalization ability of our method.

关键词： Training Decoding Semantics Data models Acoustics Electronic mail Benchmark testing Transformers Robustness Perturbation methods

来源：评论

学校读者我要写书评

暂无评论

Fast Coding Mode Decision for Intra Prediction in VVC SCC

引用

IEEE Transactions on Broadcasting 2025年第2期71卷 506-516页

作者： Dayong Wang Weihong Liu Zeyu Zhou Xin Lu Jinhua Liu Hui Guo Ce Zhu Chongqing Key Laboratory on Big Data for Bio Intelligence Chongqing University of Posts and Telecommunications Chongqing China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou University Wuzhou China School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China School of Cybersecurity Chengdu University of Information Technology Chengdu China School of Computer Science and Informatics De Montfort University Leicester U.K. School of Digital Technology Industry Shangrao Normal University Shangrao China Glasgow College and the School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China

Currently, screen content video applications are widely used in our daily lives. As the latest Screen Content Coding (SCC) standard, Versatile Video Coding (VVC) SCC employs a quad-tree plus nested multi-type tree (QTMT) coding structure and various screen content coding modes (CMs). This design enhances the coding efficiency of VVC SCC but also results in a highly complex coding process, which significantly hinders the broader adoption of screen content video technology. Consequently, improving the coding speed of VVC SCC is highly desirable. In this paper, we propose a fast CM and transform decision algorithm for Intra prediction in VVC SCC. Specifically, we initially use Convolutional Neural Networks (CNNs) to predict content types for all Coding Units (CUs). Subsequently, we predict candidate CMs for CUs based on the CM distributions of different content types. We then select the Sum of Absolute Transformed Difference (SATD) as a feature and use a naive Bayes classifier to skip unlikely Intra mode early. Finally, we terminate Block-based Differential Pulse-Code Modulation (BDPCM) early and then select the best transform type in Intra mode prediction to improve coding speed. Experimental results demonstrate that the proposed algorithm improves coding speed by an average of 39.28%, with the BDBR increasing by 0.80%.

关键词： Encoding Copper Prediction algorithms Classification algorithms Transforms Electronic mail Standards Complexity theory Training Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report 17th

Efficient Single-Image Depth Estimation on Mobile Devices, ...

引用

17th European Conference on computer vision, ECCV 2022

作者： Ignatov, Andrey Malivenko, Grigory Timofte, Radu Treszczotko, Lukasz Chang, Xin Ksiazek, Piotr Lopuszynski, Michal Pioro, Maciej Rudnicki, Rafal Smyl, Maciej Ma, Yujie Li, Zhenyu Chen, Zehui Xu, Jialei Liu, Xianming Jiang, Junjun Shi, XueChao Xu, Difan Li, Yanan Wang, Xiaotao Lei, Lei Zhang, Ziyu Wang, Yicheng Huang, Zilong Luo, Guozhong Yu, Gang Fu, Bin Li, Jiaqi Wang, Yiran Huang, Zihao Cao, Zhiguo Conde, Marcos V. Sapozhnikov, Denis Lee, Byeong Hyun Park, Dongwon Hong, Seongmin Lee, Joonhee Lee, Seunggyu Chun, Se Young Computer Vision Lab ETH Zürich Zürich Switzerland AI Witchlabs Zollikerberg Switzerland University of Wuerzburg Wuerzburg Germany TCL Research Europe Warsaw Poland Harbin Institute of Technology Harbin China Xiaomi Inc. Beijing China Tencent GY-Lab Shenzhen China National Key Laboratory of Science and Technology on Multi-Spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of

ISBN: (纸本)9783031250651

Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus, it is very crucial to have efficient and accurate depth estimation models that can run fast on low-power mobile chipsets. In this Mobile AI challenge, the target was to develop deep learning-based single image depth estimation solutions that can show a real-time performance on IoT platforms and smartphones. For this, the participants used a large-scale RGB-to-depth dataset that was collected with the ZED stereo camera capable to generated depth maps for objects located at up to 50 m. The runtime of all models was evaluated on the Raspberry Pi 4 platform, where the developed solutions were able to generate VGA resolution depth maps at up to 27 FPS while achieving high fidelity results. All models developed in the challenge are also compatible with any Android or Linux-based mobile devices, their detailed description is provided in this paper. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Slowly Expanding Neural Network for Class Incremental Learning

SSRN

引用

SSRN 2023年

作者： Xu, Zhengjin Li, Xuyang Chang, Xiaobin Zheng, Wei-Shi Wang, Ruixuan School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Department of Network Intelligence Pengcheng Laboratory Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing MOE Guangzhou China School of Artificial Intelligence Sun Yat-sen University Zhuhai China

Currently deep learning models often rapidly forget the knowledge of old classes when they are continually updated to learn knowledge of new classes. To alleviate such catastrophic forgetting issues, the state-of-the-art approach often freezes the learned feature extractor to preserve the old knowledge and introduces an additional network when learning new knowledge each time. The forgetting issue can be effectively handled by this method at the price of rapid model expansion. In this paper, we propose a novel continual learning framework, called SEIL, with a much Slower model Expansion rate and better Incremental Learning performance than its counterparts. Specifically, instead of introducing an entire feature extractor, the majority of network parameters are shared during continual learning, and only the remaining lightweight modules are expanded for each new task. An outof-the-distribution (OOD) technique is also applied to two auxiliary classifiers for more class-balanced predictions. The proposed method achieves new state-of-theart results on multiple benchmark datasets under the standard continual learning settings. The source code will be released publicly. © 2023, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Quantum Gradient Class Activation Map for Model Interpretability

arXiv

引用

arXiv 2024年

作者： Lin, Hsin-Yi Tseng, Huan-Hsin Chen, Samuel Yen-Chi Yoo, Shinjae Department of Mathematics and Computer Science Seton Hall University South OrangeNJ United States Artificial Intelligence & Machine Learning Department Brookhaven National Laboratory UptonNY United States Wells Fargo New YorkNY United States

Quantum machine learning (QML) has recently made significant advancements in various topics. Despite the successes, the safety and interpretability of QML applications have not been thoroughly investigated. This work proposes using Variational Quantum Circuits (VQCs) for activation mapping to enhance model transparency, introducing the Quantum Gradient Class Activation Map (QGrad-CAM). This hybrid quantum-classical computing framework leverages both quantum and classical strengths and gives access to the derivation of an explicit formula of feature map importance. Experimental results demonstrate significant, fine-grained, class-discriminative visual explanations generated across both image and speech datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

E2: Entropy Discrimination and Energy Optimization for Source-free Universal Domain Adaptation

E2: Entropy Discrimination and Energy Optimization for Sourc...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Meng Shen Andy J. Ma Pong C. Yuen School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Department of Computer Science Hong Kong Baptist University Hong Kong

Universal domain adaptation (UniDA) transfers knowledge under both distribution and category shifts. Most UniDA methods accessible to source-domain data during model adaptation may result in privacy policy violation and source-data transfer inefficiency. To address this issue, we propose a novel source-free UniDA method coupling confidence-guided entropy discrimination and likelihood-induced energy optimization. The entropy-based separation of target-known and unknown classes is too conservative for known-class prediction. Thus, we derive the confidence-guided entropy by scaling the normalized prediction score with the known-class confidence, that more known-class samples are correctly predicted. Due to difficult estimation of the marginal distribution without source-domain data, we constrain the target-domain marginal distribution by maximizing (minimizing) the known (unknown)-class likelihood, which equals free energy optimization. Theoretically, the overall optimization amounts to decreasing and increasing internal energy of known and unknown classes in physics, respectively. Extensive experiments demonstrate the superiority of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PLIP: Language-Image Pre-training for Person Representation Learning

arXiv

引用

arXiv 2023年

作者： Zuo, Jialong Hong, Jiahao Zhang, Feng Yu, Changqian Zhou, Hanyu Gao, Changxin Sang, Nong Wang, Jingdong National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Skywork AI Department of Computer Vision Baidu Inc China

Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory performance. The reason is that they neglect critical person-related characteristics, i.e., fine-grained attributes and identities. To address this issue, we propose a novel language-image pre-training framework for person representation learning, termed PLIP. Specifically, we elaborately design three pretext tasks: 1) Text-guided Image Colorization, aims to establish the correspondence between the person-related image regions and the fine-grained color-part textual phrases. 2) Image-guided Attributes Prediction, aims to mine fine-grained attribute information of the person body in the image;and 3) Identity-based vision-Language Contrast, aims to correlate the cross-modal representations at the identity level rather than the instance level. Moreover, to implement our pre-train framework, we construct a large-scale person dataset with image-text pairs named SYNTH-PEDES by automatically generating textual annotations. We pre-train PLIP on SYNTH-PEDES and evaluate our models by spanning downstream person-centric tasks. PLIP not only significantly improves existing methods on all these tasks, but also shows great ability in the zero-shot and domain generalization settings. © 2023, CC BY-NC-SA.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

GeoDTR+: Toward Generic Cross-View Geolocalization via Geometric Disentanglement

arXiv

引用

arXiv 2023年

作者： Zhang, Xiaohan Li, Xingyu Sultani, Waqas Chen, Chen Wshah, Safwan Department of Computer Science and Vermont Complex Systems Center University of Vermont Burlington United States Lin Gang Laboratory Shanghai China Intelligent Machine Lab Information Technology University Pakistan Center for Research in Computer Vision University of Central Florida United States

Cross-View Geo-Localization (CVGL) estimates the location of a ground image by matching it to a geo-tagged aerial image in a database. Recent works achieve outstanding progress on CVGL benchmarks. However, existing methods still suffer from poor performance in cross-area evaluation, in which the training and testing data are captured from completely distinct areas. We attribute this deficiency to the lack of ability to extract the geometric layout of visual features and models' overfitting to low-level details. Our preliminary work [1] introduced a Geometric Layout Extractor (GLE) to capture the geometric layout from input features. However, the previous GLE does not fully exploit information in the input feature. In this work, we propose GeoDTR+ with an enhanced GLE module that better models the correlations among visual features. To fully explore the LS techniques from our preliminary work, we further propose Contrastive Hard Samples Generation (CHSG) to facilitate model training. Extensive experiments show that GeoDTR+ achieves state-of-the-art (SOTA) results in cross-area evaluation on CVUSA [2], CVACT [3], and VIGOR [4] by a large margin (16.44%, 22.71%, and 13.66% without polar transformation) while keeping the same-area performance comparable to existing SOTA. Moreover, we provide detailed analyses of GeoDTR+. Our code will be available at https://***/vail-uvm/geodtr_plus. Copyright © 2023, The Authors. All rights reserved.

关键词： Antenna grounds

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：