检索结果-内蒙古大学图书馆

Decomposition and Reorganization of Phonetic Information for Speaker Embedding Learning

IEEE/ACM Transactions on Audio Speech and Language Processing 2023年 31卷 1745-1757页

作者： Hong, Qian-Bei Wu, Chung-Hsien Wang, Hsin-Min National Cheng Kung University and Academia Sinica Graduate Program of Multimedia Systems and Intelligent Computing Tainan701 Taiwan Academia Sinica Taipei115 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan701401 Taiwan Academia Sinica Institute of Information Science Taipei115 Taiwan

Speech content is closely related to the stability of speaker embeddings in speaker verification tasks. In this paper, we propose a novel architecture based on self-constraint learning (SCL) and reconstruction task (RT) to remove the influence of phonetic information on speaker embedding generation. First, SCL is used to reduce the divergence of frame-level features, which can avoid ambiguity between the resulting embeddings of the two utterances being compared. Second, RT is used to further remove phonetic information in frame-level layers, focusing on speaker-discriminative feature transformation. In our experiments, the speaker embedding models were trained on the VoxCeleb2 dataset and evaluated on the VoxCeleb1, Librispeech, SITW and VoxMovies datasets. Experimental results on VoxCeleb1 show that the proposed DROP-TDNN system reduced the EER by 7.5%, compared to the state-of-the-art ECAPA-TDNN system. Furthermore, the proposed DROP-TDNN system also outperformed the ECAPA-TDNN system in the experiments on SITW, Librispeech and VoxMovies under cross-dataset conditions. In the experiments on SITW, the proposed system reduced the EER by 3.4% compared to the ECAPA-TDNN system. In the experiments on Librispeech, the proposed system demonstrated the advantage of removing phonetic information under the clean speech condition, with a significant reduction of 25.5% in EER compared to the ECAPA-TDNN system. In the experiments on VoxMovies, the proposed system reduced the EER by up to 7.9% compared to the ECAPA-TDNN system under different pronunciation and background conditions. © 2014 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Recurrent Neural Network-based Models as Bahasa Indonesia-Sundanese Language Neural Machine Translator

Recurrent Neural Network-based Models as Bahasa Indonesia-Su...

引用

2023 International Conference on computer Science, Information Technology and Engineering, ICCoSITE 2023

作者： Wijanarko, Bambang Dwi Heryadi, Yaya Murad, Dina Fitria Tho, Cuk Hashimoto, Kiyota BINUS Online Learning Computer Science Department Bina Nusantara University Jakarta11480 Indonesia BINUS Graduate Program - Doctor of Computer Science Computer Science Department Bina Nusantara University Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Bina Nusantara University Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

Sequential data are available in many domains including weather observation data, stock price, gene sequence, and many others. Sequential data processing is very instrumental as a solution to a variety of downstream tasks in Natural Language Processing such as language translation. Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. However, language translation is not an easy computation task when there is a language-resource gap. This paper presents some empirical results from the exploration of the Recurrent Neural Network (RNN), the Gated Recurrent Unit (GRU), the Long Short-term Memory (LSTM), and the Bidirectional Long Short-term Memory (Bi-LSTM) models as machine translation models from Bahasa Indonesia to the Sundanese language. These empirical results show that the Bi-LSTM achieved the highest performance (0.95 average training accuracy and 0.92 average testings BLEU score) compared to the RNN (0.93 average training accuracy and 0.91 average testings BLEU score), the GRU (0.88 average training accuracy and 0.89 average testings BLEU score), and the LSTM (0.92 average training accuracy and 0.91 average testings BLEU score) models. These results validate some previously reported studies that claim the Bi-LSTM model potentially outperforms the other recurrent neural network-based models when it is used to process sequence datasets. © 2023 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

Neural Machine Translation Approach for Low-resource Languages using Long Short-term Memory Model

Neural Machine Translation Approach for Low-resource Languag...

引用

2023 International Conference on computer Science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Murad, Dina Fitria Tho, Cuk Hashimoto, Kiyota Bina Nusantara University BINUS Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Computer Science Department Bina Nusantara University Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Bina Nusantara University Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

Communication is a form of translation that human learns naturally since early childhood. Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. One example of high-impact language translation is translating health protocols from the World Health Organization to many national languages to prevent the spread of the Covid-19 virus. However, the language translation is not an easy computation task when there is a language-resource gap. This paper presents empirical results on the performance of the Long Short-term Memory model as a machine translation involving Bahasa Indonesia and the Sundanese languages. Performance of the Sundanese language to Indonesian language translation is 0.93 average training and validation accuracy and 0.91 average testings BLEU score. Whilst, Indonesian language to Sundanese language translation is 0.92 average training and validation accuracy and 0.88 average testings BLEU score. Both models achieve 0.39 average training loss and 0.38 average validation loss. © 2023 IEEE.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

Fostering Digital Innovation in Indonesia: The Role of STEM-AI Skills in Overcoming Talent Deficits and Gender Stereotypes

Fostering Digital Innovation in Indonesia: The Role of STEM-...

引用

Intelligent Cybernetics Technology & Applications (ICICyTA), International Conference on

作者： Erwin Halim Amalia Zahra Maryani Lili Ayu Wulandhari Devi Fitrianah Virienia Puspita Information Systems Department School of Information Systems Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Communication Department BINUS Graduate Program Master of Strategic Marketing Communication Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331506490

ISBN: (纸本)9798331506506

This research explores the optimization of digital talent in advanced industries, particularly in the context of rapid digital transformation. Despite the increasing importance of digital talent for gaining a competitive edge, several challenges persist. In Indonesia, for example, there is a significant shortage of digitally skilled workers, with the World Bank reporting a gap of 9 million skilled individuals over the past 15 years. Additionally, artificial intelligence (AI) is expected to impact 9.5 million jobs, further exacerbating the demand for digital skills. Furthermore, the employability of graduates remains low, largely due to inadequate training, poor language proficiency, and limited cultural sensitivity. Many companies face difficulties in finding qualified individuals, quickly upskilling their workforce, and fostering an innovative organizational culture. This study seeks to evaluate the factors influencing digital talent performance in the context of these challenges. It examines seven key variables: digital readiness, digital technology adoption, relevance of AI, digital skills, individual performance, problem-solving ability, and overall digital talent performance. Hypotheses were tested using Partial Least Squares Structural Equation Modeling (PLS-SEM). Data was collected from 378 participants, primarily students with STEM backgrounds, in the Jabodetabek area of Indonesia in November 2024. The findings reveal that all hypotheses are significant, with results indicating that user satisfaction and the perceived value of digital talent in Indonesia have a notable impact on continued usage intentions in digital roles.

关键词： Training Industries Technological innovation Sensitivity Mathematical models Problem-solving Artificial intelligence Optimization Faces Gender issues

来源：评论

学校读者我要写书评

暂无评论

The Impact of Recommendation System Provided Based on Online Learning Readiness in the MOOC Environment 24

The Impact of Recommendation System Provided Based on Online...

引用

24th International Arab Conference on Information Technology, ACIT 2023

作者： Murad, Dina Fitria Toha, Mohamad Mayatopani, Hendra Dewi, Meta Amalya Leandros, Riyan Murad, Silvia Ayunda Heryadi, Yaya Wijanarko, Bambang Dwi Bina Nusantara University Information Systems Department Binus Online Learning Jakarta Indonesia Universitas Terbuka Jakarta Indonesia Pradita University Department of Information System Tangerang Indonesia Bina Nusantara University Computer Science Department Binus Graduate Program Doctor of Computer Science Jakarta Indonesia Bina Nusantara University School of Computer Science Jakarta Indonesia

ISBN: (纸本)9798350384307

MOOCs are one of the developments or impacts of e-learning or online learning. Massive Open Online Course (MOOC) is one of the choices for students to increase their knowledge through non-formal channels. Our research aims to determine the level of readiness of students regarding MOOC learning and opportunities for utilizing recommendation systems in students' decision-making regarding selecting MOOCs that suit their interests and needs. We conducted a survey regarding the constraints and needs of learner readiness through 5 aspects, namely 1) technical aspect, (2) social aspect, (3) communication aspect, (4) lecture readiness aspect, and (5) online discussion. The results of this research show that the main challenges that MOOC participants may face in a MOOC environment are Technical Aspects (28.25%), Social Aspects (21.47%), and Communication Aspects (18.93%). Meanwhile, the greatest strength of online learning in the MOOC environment is the social aspect (21%), the most influential and continued with technical and other aspects. Meanwhile, the lecture readiness aspect is quite good, and the online discussion aspect is the biggest aspect that influences the success of MOOC learning. Other results of this research indicate the importance of a recommendation system for MOOC students to make it easier for students to choose the right MOOC according to their interests and needs. © 2023 IEEE.

关键词： MOOC personalization Recommendation system student competency Technology Enhanced Learning

来源：评论

学校读者我要写书评

暂无评论

Revalidating the Encoder-Decoder Depths and Activation Function to Find Optimum Vanilla Transformer Model

Revalidating the Encoder-Decoder Depths and Activation Funct...

引用

2023 International Conference on computer Science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Fitria Murad, Dina Tho, Cuk Hashimoto, Kiyota Bina Nusantara University Graduate Program- Computer Science Computer Science Department BINUS Jakarta11480 Indonesia Bina Nusantara University Online Learning Computer Science Department BINUS Jakarta11480 Indonesia Bina Nusantara University BINUS Online Learning Information Systems Department Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

The transformer model has become a state-of-the-art model in Natural Language Processing. The initial transformer model, known as the vanilla transformer model, is designed to improve some prominent models in sequence modeling and transduction problems such as language modeling and machine translation. The initial transformer model has 6 stacks of identical encoder-decoder layers with an attention mechanism whose aim is to push limitations of common recurrent language models and encoder-decoder architectures. Its outstanding performance has inspired many researchers to extend the architecture to improve its performance and computation efficiency. Despite many extensions to the vanilla transformer, there is no clear explanation of the encoder-decoder set out depth in the vanilla transformer model. This paper presents exploration results on the effect of combination encoder-decoder layer depth and activation function in the feed-forward layer of the vanilla transformer model on its performance. The model is tested to address a downstream task: text translation from Bahasa Indonesia to the Sundanese language. Although the value difference is not significantly large, the empirical results show that the combination of depth = 2 with Sigmoid, Tanh, and ReLU activation function;and d = 6 with ReLU activation shows the highest average training accuracy. Interestingly, d = 6 and ReLU show the lowest average training and validation loss. However, statistically, there is no significant difference between depth and activation functions. © 2023 IEEE.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Indonesian-Sundanese Language Machine Translation using Bidirectional Long Short-term Memory Model

Indonesian-Sundanese Language Machine Translation using Bidi...

引用

2023 International Conference on computer Science, Information Technology and Engineering, ICCoSITE 2023

作者： Heryadi, Yaya Wijanarko, Bambang Dwi Fitria Murad, Dina Tho, Cuk Hashimoto, Kiyota BINUS Graduate Program - Doctor of Computer Science Computer Science Department Bina Nusantara University Jakarta11480 Indonesia BINUS Online Learning Bina Nusantara University Computer Science Department Jakarta11480 Indonesia BINUS Online Learning Information Systems Department Bina Nusantara University Jakarta11480 Indonesia Prince of Songkla University Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Phuket83120 Thailand

ISBN: (纸本)9798350320954

Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. However, the language translation is not an easy computation task when there is a language-resource gap. This paper presents empirical results on the performance of two models: the Long Short-term Memory and the Bidirectional Long Short-term Memory models as machine language translation models involving Bahasa Indonesia and the Sundanese language. The empiric results showed that the Bidirectional Long Short-term Memory model achieves higher performance as a language translator from the Sundanese language to Bahasa Indonesia and vice versa (0.95 and 0.95 average training accuracy respectively;and 0.90 and 0.89 average testing BLEU scores respectively) than the Long Short-term Memory model as a language translator from the Sundanese language to Bahasa Indonesia and vice versa (0.93 and 0.92 average training accuracy respectively;and 0.91 and 0.88 average testing BLEU scores). These results validate some previously reported studies that claim the Bidirectional Long Short-term Memory model potentially outperform the Long Short-term Memory model when it is used to process a sequence dataset. © 2023 IEEE.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

The Age and Updating Stability for a Communication Context in VANET

The Age and Updating Stability for a Communication Context i...

引用

Brazilian Symposium on Computing System Engineering (SBESC)

作者： Margarete De Sá Sérgio Gorender Distributed Systems Laboratory (LaSiD) Graduate Program in Mechatronics (PPGM) Computer Science Institute (IC) and Polytechnic School (EP) Federal University of Bahia (UFBA)

ISBN: (数字)9798331509002

ISBN: (纸本)9798331532857

VANETs make it possible to execute specific vehicular applications, in particular those with the aim of turning traffic safe and avoiding congestion. However, it is difficult to maintain communication between vehicles when these vehicles move dynamically at high speeds. Context-aware systems have been studied as a way to monitor context information from sensors, which can be used by systems to adapt to changes in their environment or in application requirements. This concept is used by VANET protocols and applications in different ways. Quality of Context (QoC) metrics are used to qualify the context information considering different characteristics of sensors and of the information, being a base for systems to decide if it is safe and interesting to use specific information. In this paper, we propose QoC metrics related to the stability of the updating process for a vehicular communication context. In addition, we also analyze the Age QoC metric and show how to calculate it for distinct context information. We simulate scenarios to verify the QoC metrics behavior. The results showed that the proposed QoC metrics can properly qualify the vehicular communication context.

关键词： Measurement Roads Vehicular ad hoc networks Sensor phenomena and characterization Turning systems engineering and theory Stability analysis Sensor systems Reliability Monitoring

来源：评论

学校读者我要写书评

暂无评论

Potentials and Challenges in Combining the Internet of Things and Augmented Reality: a Systematic Literature Review 1

Potentials and Challenges in Combining the Internet of Thing...

引用

1st International Conference on Smart Technology, Applied Informatics, and Engineering, APICS 2022

作者： Arin, Ikrar Adinata Meyliana Prabowo, Harjanto Hidayanto, Achmad Nizar Binus Graduate Program Computer Science Information System Department School of Information Systems Bina Nusantara University Computer Science Department Jakarta Indonesia School of Information Systems Bina Nusantara University Information System Department Jakarta Indonesia Binus Business School Undergraduate Program Bina Nusantara University Management Department Jakarta Indonesia Universitas Indonesia Faculty of Computer Science Jakarta Indonesia

ISBN: (数字)9781665489850

ISBN: (纸本)9781665489850

The line between the real world and the internet is blurred by augmented reality (AR). The internet of things (IoT) is transforming the way we communicate with the rest of the world. AR is a promising technology that is emerging as a key to unlocking the full potential of the IoT. The potential and challenges of combining the internet of things with augmented reality are investigated in this study. After a rigorous searching process, around fifty-one (51) publications were chosen and thoroughly examined to summarize the most recent developments in this field. In terms of research findings, four main clusters of potential benefits were identified: visualization sensor data, human-object interaction, application diversity, and IoT use case adoption. In contrast, the challenges posed by IoT and AR combinations were clustered around technical, organizational, and ergonomic considerations. The accumulation of knowledge and actionable insights will benefit both academics and practitioners interested in which a revolution will create by these emerging technology. © 2022 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Automatic Smart Crawling on Twitter for Weather Information in Indonesia 8

Automatic Smart Crawling on Twitter for Weather Information ...

引用

8th International Conference on computer Science and Computational Intelligence, ICCSCI 2023

作者： Purwandari, Kartika Perdana, Reza Bayu Sigalingging, Join W.C. Rahutomo, Reza Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Database Center Division of BMKG Meteorological Climatological and Geophysical Agency Jakarta10720 Indonesia Information Systems Department School of Information Systems Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Although Twitter is a popular platform for social interaction analysis and text data mining, it faces challenges with geolocation automation. To address this problem, the researchers propose the utilization of a Support Vector Machine (SVM) model to develop an automated Twitter crawling system. The system aims to collect data related to weather in Indonesia by employing Twin, a Python-based Twitter scraping software. To overcome null geolocations, the study incorporates aliases created based on the common practice of Indonesian users mentioning the country's location in tweets. The results demonstrate that the SVM model, combined with automated smart crawling, achieves an 85% accuracy rate. © 2023 The Authors. Published by Elsevier B.V.

关键词： smart crawling Social media SVM Twitter weather

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：