Pub Date : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979937
Mohammad Imron, A. Hidayanto, W. R. Fitriani, W. S. Nugroho, D. I. Inan
Indonesia economics is dominated by micro, small, and medium enterprises (MSMEs). One of many ways to develop SMEs in Indonesia is to develop the quality of human resource (HR) development. Human resource information system (HRIS) can help HR development process to be more effective, efficient, and productive. Cloud-based HRIS is one of the solutions that can be used by MSMEs since it’s more affordable than HRIS in general. There are many factors influence MSMEs to adopt cloud-based HRIS. This research discussed about factors ranking of cloud-based HRIS adoption by SMEs in Jakarta, Bogor, Depok, Tangerang, and Bekasi (Jabodetabek). The factors were adopted from many theories and implemented using technology-organization-environment (TOE) framework. This research used analytic hierarchy process (AHP). Semi-structured interview also used to validate the results. The results concluded that organization factor is the most important factor to adopt cloudbased HRIS.
{"title":"Analysis of Cloud-Based Human Resource Information System Adoption Factors Prioritization in Micro, Small, and Medium Enterprises","authors":"Mohammad Imron, A. Hidayanto, W. R. Fitriani, W. S. Nugroho, D. I. Inan","doi":"10.1109/ICACSIS47736.2019.8979937","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979937","url":null,"abstract":"Indonesia economics is dominated by micro, small, and medium enterprises (MSMEs). One of many ways to develop SMEs in Indonesia is to develop the quality of human resource (HR) development. Human resource information system (HRIS) can help HR development process to be more effective, efficient, and productive. Cloud-based HRIS is one of the solutions that can be used by MSMEs since it’s more affordable than HRIS in general. There are many factors influence MSMEs to adopt cloud-based HRIS. This research discussed about factors ranking of cloud-based HRIS adoption by SMEs in Jakarta, Bogor, Depok, Tangerang, and Bekasi (Jabodetabek). The factors were adopted from many theories and implemented using technology-organization-environment (TOE) framework. This research used analytic hierarchy process (AHP). Semi-structured interview also used to validate the results. The results concluded that organization factor is the most important factor to adopt cloudbased HRIS.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115392274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979756
Nabilah Zhafira Viderisa, H. Santoso, R. Isal
There are a lot of growing e-Commerce companies in Indonesia with their own application that has been used by millions of users. One of the important informational channels in e-Commerce application is push notifications, of which its sole purpose is to push and deliver information to its users. The problem is that only a limited number of customers open push notifications immediately upon receiving. This research was conducted to find the key factors that determine user‘s desires to open push notification and to improve user‘s experiences when receiving push notifications. User-Centered Design and a mixed-method approach were used on this research, utilizing surveys and contextual interviews for data collection. Tokopedia is one of e-Commerce companies in Indonesia. Tokopedia iOS application is used in this research as a case study as Tokopedia is one of the most used e-Commerce application in Indonesia. The research findings show that the key determining factors are contents of the push notifications and time and frequency of receipt. Based on the results, a prototype has been designed in a high-fidelity form and was subsequently evaluated using the Usability Testing method. The evaluation show that the task success rate of said prototype is 88.3 percent, and accordingly it could be the solution to this problems.
{"title":"Designing the Prototype of Personalized Push Notifications on E-Commerce Application with the User-Centered Design Method","authors":"Nabilah Zhafira Viderisa, H. Santoso, R. Isal","doi":"10.1109/ICACSIS47736.2019.8979756","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979756","url":null,"abstract":"There are a lot of growing e-Commerce companies in Indonesia with their own application that has been used by millions of users. One of the important informational channels in e-Commerce application is push notifications, of which its sole purpose is to push and deliver information to its users. The problem is that only a limited number of customers open push notifications immediately upon receiving. This research was conducted to find the key factors that determine user‘s desires to open push notification and to improve user‘s experiences when receiving push notifications. User-Centered Design and a mixed-method approach were used on this research, utilizing surveys and contextual interviews for data collection. Tokopedia is one of e-Commerce companies in Indonesia. Tokopedia iOS application is used in this research as a case study as Tokopedia is one of the most used e-Commerce application in Indonesia. The research findings show that the key determining factors are contents of the push notifications and time and frequency of receipt. Based on the results, a prototype has been designed in a high-fidelity form and was subsequently evaluated using the Usability Testing method. The evaluation show that the task success rate of said prototype is 88.3 percent, and accordingly it could be the solution to this problems.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116937114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979733
Abdurrahman, A. Purwarianti
Machine learning based text processing relies on a qualified text dataset. Text augmentation research aims to enrich text dataset in order to gain higher performance compared to the one using original text dataset. We have conducted text augmentation process on Indonesian text classification by replacing certain words with their synonyms. The process consists of determining the number of words to be substituted in the sentence and selecting the substitute word from the synonym list. The first process, determining the number of words to be substituted, is done using augmentation degree. The second process, selecting the best substitute word, is done using language model. The synonym list is built from thesaurus. We compared several options in building language model. Statistical model is built using combinations of n-gram and smoothing while simple neural model is built using gram value of 3 and 5. The neural model uses pre trained word embedding as input. 5-gram neural model excels other language model setup by significant value of perplexity. Using the best language model, augmented dataset is generated and applied on two classification task of aspect-based sentiment analysis: aspect categorization and sentiment classification. Experiments were done using augmentation degree of 0.1 to 1. The best augmentation degree yields a better 3-4% on classification model’s performance.
{"title":"Effective Use of Augmentation Degree and Language Model for Synonym-based Text Augmentation on Indonesian Text Classification","authors":"Abdurrahman, A. Purwarianti","doi":"10.1109/ICACSIS47736.2019.8979733","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979733","url":null,"abstract":"Machine learning based text processing relies on a qualified text dataset. Text augmentation research aims to enrich text dataset in order to gain higher performance compared to the one using original text dataset. We have conducted text augmentation process on Indonesian text classification by replacing certain words with their synonyms. The process consists of determining the number of words to be substituted in the sentence and selecting the substitute word from the synonym list. The first process, determining the number of words to be substituted, is done using augmentation degree. The second process, selecting the best substitute word, is done using language model. The synonym list is built from thesaurus. We compared several options in building language model. Statistical model is built using combinations of n-gram and smoothing while simple neural model is built using gram value of 3 and 5. The neural model uses pre trained word embedding as input. 5-gram neural model excels other language model setup by significant value of perplexity. Using the best language model, augmented dataset is generated and applied on two classification task of aspect-based sentiment analysis: aspect categorization and sentiment classification. Experiments were done using augmentation degree of 0.1 to 1. The best augmentation degree yields a better 3-4% on classification model’s performance.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120868042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/icacsis47736.2019.8979674
{"title":"ICACSIS 2019 Welcome Message from Dean of Faculty of Computer Science Universitas Indonesia","authors":"","doi":"10.1109/icacsis47736.2019.8979674","DOIUrl":"https://doi.org/10.1109/icacsis47736.2019.8979674","url":null,"abstract":"","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128563988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979689
Munadia Rahma Hanifa, H. Santoso, Kasiyah
Massive Open Online Course (MOOC) is one of the online learning implementations. The average of the completion rate from the courses in MOOC is still relatively low. The participants of the study are people from Indonesia and most of them are workers, students, and college students. This research aimed to determine the extent to which the MOOC Coursera platform follows the principles of the instructional design and interface design i.e., Gagné’s Nine Events of Instruction, Chickering and Gamson’s Seven Principles for Good Practice in Undergraduate Education, and Shneiderman’s Eight Golden Rules of the Interface Design. Moreover, this research was also reviewed from the usability aspect. The study showed that Coursera has implemented all of the instructional design principles and seven from eight points of interface design principles. This research also proposed improvement recommendations based on the results of data analysis from respondents who were mostly from areas on the island of Java namely Jakarta, Bogor, Depok, Tangerang and Bekasi (Jabodetabek).
{"title":"Evaluation and Recommendations for the Instructional Design and User Interface Design of Coursera MOOC Platform","authors":"Munadia Rahma Hanifa, H. Santoso, Kasiyah","doi":"10.1109/ICACSIS47736.2019.8979689","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979689","url":null,"abstract":"Massive Open Online Course (MOOC) is one of the online learning implementations. The average of the completion rate from the courses in MOOC is still relatively low. The participants of the study are people from Indonesia and most of them are workers, students, and college students. This research aimed to determine the extent to which the MOOC Coursera platform follows the principles of the instructional design and interface design i.e., Gagné’s Nine Events of Instruction, Chickering and Gamson’s Seven Principles for Good Practice in Undergraduate Education, and Shneiderman’s Eight Golden Rules of the Interface Design. Moreover, this research was also reviewed from the usability aspect. The study showed that Coursera has implemented all of the instructional design principles and seven from eight points of interface design principles. This research also proposed improvement recommendations based on the results of data analysis from respondents who were mostly from areas on the island of Java namely Jakarta, Bogor, Depok, Tangerang and Bekasi (Jabodetabek).","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113958412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979959
Erryan Sazany, I. Budi
Some researches had succeeded in doing hate speech identification automatically from text with machine learning and deep learning approaches. However, it was still unclear how adaptive is a deep learning-based model if it is tested on a different set of text data with different domain. To address this issue, this research proposed some deep learning-based methods, using some variants of Recurrent Neural Network to identify hate speech in texts sourced from Twitter, and then used to predict other set of text data sourced from Facebook and Twitter. The experiment was done in order to measure the difference of model performance between training phase and testing phase. Experiment results showed that the proposed method outperformed the machine learning based methods, both in training phase, by GRU algorithm with 85.37% F1-score, and in testing phase, by LSTM algorithm with 76.30% F1-score. Then, in terms of adaptability of model performance, the proposed method gave comparable result against the baseline method.
{"title":"Hate Speech Identification in Text Written in Indonesian with Recurrent Neural Network","authors":"Erryan Sazany, I. Budi","doi":"10.1109/ICACSIS47736.2019.8979959","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979959","url":null,"abstract":"Some researches had succeeded in doing hate speech identification automatically from text with machine learning and deep learning approaches. However, it was still unclear how adaptive is a deep learning-based model if it is tested on a different set of text data with different domain. To address this issue, this research proposed some deep learning-based methods, using some variants of Recurrent Neural Network to identify hate speech in texts sourced from Twitter, and then used to predict other set of text data sourced from Facebook and Twitter. The experiment was done in order to measure the difference of model performance between training phase and testing phase. Experiment results showed that the proposed method outperformed the machine learning based methods, both in training phase, by GRU algorithm with 85.37% F1-score, and in testing phase, by LSTM algorithm with 76.30% F1-score. Then, in terms of adaptability of model performance, the proposed method gave comparable result against the baseline method.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126444033","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/icacsis47736.2019.8979763
{"title":"ICACSIS 2019 Program Schedule","authors":"","doi":"10.1109/icacsis47736.2019.8979763","DOIUrl":"https://doi.org/10.1109/icacsis47736.2019.8979763","url":null,"abstract":"","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126569085","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979771
S. Aditya, H. Santoso, R. Isal
The use of information technology in the eLearning process gives positive and negative impacts. One of the positive impacts is the easy access for vast information; while the negative impacts is the ineffective learning because it makes students lazy. Previous research has used games or game elements to decrease the negative impacts of e-Learning. A survey about Algorithm Design and Analysis course was conducted, and it shows that there are some difficult subjects that need to be taught using an alternative method of learning. This research discusses how to design a video game in order to learn branch and bound algorithm and evaluate the game produced with the design. First, online surveys were done to gather the requirement, then the game design was made, then the game was implemented and evaluated. The evaluation would be used to make a better design for the next development iteration. The result of playtesting shows positive feedbacks and receives critics and suggestions. This research finds that designing a good game for learning is hard because developer must carefully define all elements in the game, so that everything is balanced and complements each other.
{"title":"Developing a Game-Based Learning for Branch and Bound Algorithm","authors":"S. Aditya, H. Santoso, R. Isal","doi":"10.1109/ICACSIS47736.2019.8979771","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979771","url":null,"abstract":"The use of information technology in the eLearning process gives positive and negative impacts. One of the positive impacts is the easy access for vast information; while the negative impacts is the ineffective learning because it makes students lazy. Previous research has used games or game elements to decrease the negative impacts of e-Learning. A survey about Algorithm Design and Analysis course was conducted, and it shows that there are some difficult subjects that need to be taught using an alternative method of learning. This research discusses how to design a video game in order to learn branch and bound algorithm and evaluate the game produced with the design. First, online surveys were done to gather the requirement, then the game design was made, then the game was implemented and evaluated. The evaluation would be used to make a better design for the next development iteration. The result of playtesting shows positive feedbacks and receives critics and suggestions. This research finds that designing a good game for learning is hard because developer must carefully define all elements in the game, so that everything is balanced and complements each other.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121612827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979772
Noer Fitria Putra Setyono, Erdefi Rakun
SIBI is a sign language that is officially used in Indonesia. The use of SIBI is often found to be a problem because of the many gestures that have to be remembered. This study aims to recognize SIBI gestures by extracting hand and facial features which are then classified using Bidirectional Long ShortTerm Memory (BiLSTM). The feature extraction used in this research is Deep Convolutional Neural Network (DeepCNN) such as ResNet50 and MobileNetV2, where both models are used as a comparison. This study also compares the performance and computational time between the two models which is expected to be applied to smartphones later, where both models can now be implemented on smartphones. The results showed that the use of ResNet50-BiLSTM model have better performance than MobileNetV2-BiLSTM which is 99.89%. However, if it will be applied to mobile architecture, MobileNetV2-BiLSTM is superior because it has a faster computational time with a performance that is not significantly different when compared to ResNet50-BiLSTM.
{"title":"Recognizing Word Gesture in Sign System for Indonesian Language (SIBI) Sentences Using DeepCNN and BiLSTM","authors":"Noer Fitria Putra Setyono, Erdefi Rakun","doi":"10.1109/ICACSIS47736.2019.8979772","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979772","url":null,"abstract":"SIBI is a sign language that is officially used in Indonesia. The use of SIBI is often found to be a problem because of the many gestures that have to be remembered. This study aims to recognize SIBI gestures by extracting hand and facial features which are then classified using Bidirectional Long ShortTerm Memory (BiLSTM). The feature extraction used in this research is Deep Convolutional Neural Network (DeepCNN) such as ResNet50 and MobileNetV2, where both models are used as a comparison. This study also compares the performance and computational time between the two models which is expected to be applied to smartphones later, where both models can now be implemented on smartphones. The results showed that the use of ResNet50-BiLSTM model have better performance than MobileNetV2-BiLSTM which is 99.89%. However, if it will be applied to mobile architecture, MobileNetV2-BiLSTM is superior because it has a faster computational time with a performance that is not significantly different when compared to ResNet50-BiLSTM.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131764474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979939
M. Saputri, M. Adriani
Local languages are the most widely used as communication media in the daily conversations of Indonesian people. Preserving those local languages is crucial, especially for maintaining language and cultural identities. However, the variety of local languages raises communication problems. One of initial solution is developing a spoken language identification system to recognize different languages. This study developed a system of spoken language identification from speech data for Indonesian local languages, including Javanese, Sundanese, Madurese, Minangkabau, and Musi. The dataset used in this study is spontaneous speech data collected from local radio broadcasts for each language. This spontaneous dataset contains a lot of noises. Therefore, the suitable feature extraction and classification methods are required for developing a robust language identification system. In this study, three features are combined to identify languages, namely acoustic features based on i-vector, phonotactic features based on parallel phonemes and the dynamic prosody feature. Those features are merged on the hidden layer of Deep Neural Network (DNN). The experimental results showed that the f1-score achieved by combining those features with DNN on speech data with 3 seconds, 10 seconds and 30 seconds duration are 87.85%, 93.46%, and 96.73% respectively.
{"title":"Identifying Indonesian Local Languages on Spontaneous Speech Data","authors":"M. Saputri, M. Adriani","doi":"10.1109/ICACSIS47736.2019.8979939","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979939","url":null,"abstract":"Local languages are the most widely used as communication media in the daily conversations of Indonesian people. Preserving those local languages is crucial, especially for maintaining language and cultural identities. However, the variety of local languages raises communication problems. One of initial solution is developing a spoken language identification system to recognize different languages. This study developed a system of spoken language identification from speech data for Indonesian local languages, including Javanese, Sundanese, Madurese, Minangkabau, and Musi. The dataset used in this study is spontaneous speech data collected from local radio broadcasts for each language. This spontaneous dataset contains a lot of noises. Therefore, the suitable feature extraction and classification methods are required for developing a robust language identification system. In this study, three features are combined to identify languages, namely acoustic features based on i-vector, phonotactic features based on parallel phonemes and the dynamic prosody feature. Those features are merged on the hidden layer of Deep Neural Network (DNN). The experimental results showed that the f1-score achieved by combining those features with DNN on speech data with 3 seconds, 10 seconds and 30 seconds duration are 87.85%, 93.46%, and 96.73% respectively.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132615714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：