发布求助
文献互助 智能选刊 最新文献

From Natural to Artificial Intelligence - Algorithms and Applications最新文献

筛选
英文 中文
Convolutional Neural Networks for Raw Speech Recognition 原始语音识别的卷积神经网络
From Natural to Artificial Intelligence - Algorithms and Applications Pub Date : 2018-12-12 DOI: 10.5772/INTECHOPEN.80026
Vishal Passricha, R. Aggarwal
{"title":"Convolutional Neural Networks for Raw Speech Recognition","authors":"Vishal Passricha, R. Aggarwal","doi":"10.5772/INTECHOPEN.80026","DOIUrl":"https://doi.org/10.5772/INTECHOPEN.80026","url":null,"abstract":"State-of-the-art automatic speech recognition (ASR) systems map the speech signal into its corresponding text. Traditional ASR systems are based on Gaussian mixture model. The emergence of deep learning drastically improved the recognition rate of ASR systems. Such systems are replacing traditional ASR systems. These systems can also be trained in end-to-end manner. End-to-end ASR systems are gaining much popularity due to simpli- fied model-building process and abilities to directly map speech into the text without any predefined alignments. Three major types of end-to-end architectures for ASR are atten- tion-based methods, connectionist temporal classification, and convolutional neural network (CNN)-based direct raw speech model. In this chapter, CNN-based acoustic model for raw speech signal is discussed. It establishes the relation between raw speech signal and phones in a data-driven manner. Relevant features and classifier both are jointly learned from the raw speech. Raw speech is processed by first convolutional layer to learn the feature representation. The output of first convolutional layer, that is, intermediate representation, is more discriminative and further processed by rest convolutional layers. This system uses only few parameters and performs better than traditional cepstral fea- ture-based systems. The performance of the system is evaluated for TIMIT and claimed similar performance as MFCC.","PeriodicalId":289041,"journal":{"name":"From Natural to Artificial Intelligence - Algorithms and Applications","volume":"166 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114732709","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}
引用次数: 22
Hard, firm, soft … Etherealware:Computing by Temporal Order of Clocking 硬的，坚固的，软的……以太坊:按时间顺序计算
From Natural to Artificial Intelligence - Algorithms and Applications Pub Date : 2018-11-05 DOI: 10.5772/INTECHOPEN.80432
M. Vielhaber
{"title":"Hard, firm, soft … Etherealware:Computing by Temporal Order of Clocking","authors":"M. Vielhaber","doi":"10.5772/INTECHOPEN.80432","DOIUrl":"https://doi.org/10.5772/INTECHOPEN.80432","url":null,"abstract":"We define Etherealware as the concept of implementing the functionality of an algorithm by means of the clocking scheme of a cellular automaton (CA). We show, which functions can be implemented in this way, and by which CAs.","PeriodicalId":289041,"journal":{"name":"From Natural to Artificial Intelligence - Algorithms and Applications","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121931549","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}
引用次数: 0
Evaluation between Virtual Acoustic Model and Real Acoustic Scenarios for Urban Representation 城市表征的虚拟声学模型与真实声学场景的评价
From Natural to Artificial Intelligence - Algorithms and Applications Pub Date : 2018-11-05 DOI: 10.5772/INTECHOPEN.78330
Josep Llorca, Héctor Zapata, J. Alba, E. Redondo, D. Fonseca
{"title":"Evaluation between Virtual Acoustic Model and Real Acoustic Scenarios for Urban Representation","authors":"Josep Llorca, Héctor Zapata, J. Alba, E. Redondo, D. Fonseca","doi":"10.5772/INTECHOPEN.78330","DOIUrl":"https://doi.org/10.5772/INTECHOPEN.78330","url":null,"abstract":"Audio representation is critical for immersive virtual environments. This article presents a quasi-experiment based on architecture students evaluating the immersive impact of 3D audio in the representation of urban environments. In the framework of acoustic urban heritage preservation, a set of city squares with varying acoustic features were used as case studies in a two-step process: an objective analysis of the acoustic properties of these spaces; and the users’ subjective perceptions of the virtual environment of the squares. The study shows that we can gain a better understanding of the objective parameters through the subjective views of users. Acoustic heritage can be assessed subjectively using an immersive system such as virtual reality, in which audio representation is a key factor.","PeriodicalId":289041,"journal":{"name":"From Natural to Artificial Intelligence - Algorithms and Applications","volume":"53 100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121227638","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}
引用次数: 2
Face Recognition Based on Texture Descriptors 基于纹理描述符的人脸识别
From Natural to Artificial Intelligence - Algorithms and Applications Pub Date : 2018-11-05 DOI: 10.5772/INTECHOPEN.76722
J. Olivares-Mercado, K. Toscano-Medina, G. Sánchez-Pérez, M. Miyatake, H. Perez-Meana, L. C. Castro-Madrid
{"title":"Face Recognition Based on Texture Descriptors","authors":"J. Olivares-Mercado, K. Toscano-Medina, G. Sánchez-Pérez, M. Miyatake, H. Perez-Meana, L. C. Castro-Madrid","doi":"10.5772/INTECHOPEN.76722","DOIUrl":"https://doi.org/10.5772/INTECHOPEN.76722","url":null,"abstract":"","PeriodicalId":289041,"journal":{"name":"From Natural to Artificial Intelligence - Algorithms and Applications","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132786598","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}
引用次数: 0
Local Patterns for Face Recognition 人脸识别的局部模式
From Natural to Artificial Intelligence - Algorithms and Applications Pub Date : 2018-11-05 DOI: 10.5772/INTECHOPEN.76571
Chih-Wei Lin
{"title":"Local Patterns for Face Recognition","authors":"Chih-Wei Lin","doi":"10.5772/INTECHOPEN.76571","DOIUrl":"https://doi.org/10.5772/INTECHOPEN.76571","url":null,"abstract":"The main objective of the local pattern is to describe the image with high discriminative features so that the local pattern descriptors are more suitable for face recognition. The word “ local ” represents the measured image with the subregion and is the key in this chapter. Regardless of the techniques proposed, the local pattern is one of the most interesting areas in face recognition. The local facial descriptor is a local pattern that generates the descriptor by considering the subregion of an image. Techniques based on various combination methods from the local facial descriptors are not unusual. This chapter is concerned primarily to help the reader to develop a basic understanding of the local pattern descriptors and how they apply to face recognition. We begin to describe the outline of the local pattern in face recognition and its relative facial descriptors. Next, we give an introduction to the popular local patterns and establish examples to demonstrate the process of each method. To the end of this chapter, we conclude those methods with a discussion of issues related to the properties of the local patterns.","PeriodicalId":289041,"journal":{"name":"From Natural to Artificial Intelligence - Algorithms and Applications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130393365","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}
引用次数: 1
Learning Algorithms for Fuzzy Inference Systems Using Vector Quantization 基于矢量量化的模糊推理系统学习算法
From Natural to Artificial Intelligence - Algorithms and Applications Pub Date : 2018-11-05 DOI: 10.5772/INTECHOPEN.79925
H. Miyajima, Noritaka Shigei, H. Miyajima
{"title":"Learning Algorithms for Fuzzy Inference Systems Using Vector Quantization","authors":"H. Miyajima, Noritaka Shigei, H. Miyajima","doi":"10.5772/INTECHOPEN.79925","DOIUrl":"https://doi.org/10.5772/INTECHOPEN.79925","url":null,"abstract":"Many studies on learning of fuzzy inference systems have been made. Specifically, it is known that learning methods using vector quantization (VQ) and steepest descent method (SDM) are superior to other methods. In their learning methods, VQ is used only in determination of the initial parameters for the antecedent part of fuzzy rules. In order to improve them, some methods determining the initial parameters for the consequent part by VQ are proposed. For example, learning method composed of three stages as VQ, generalized inverse matrix (GIM), and SDM was proposed in the previous paper. In this paper, we will propose improved methods for learning process of SDM for learning methods using VQ, GIM, and SDM and show that the methods are superior in the number of rules to the conventional methods in numerical simulations.","PeriodicalId":289041,"journal":{"name":"From Natural to Artificial Intelligence - Algorithms and Applications","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127005035","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}
引用次数: 2
Cellular Automata and Randomization: A Structural Overview 元胞自动机与随机化:结构概述
From Natural to Artificial Intelligence - Algorithms and Applications Pub Date : 2018-11-05 DOI: 10.5772/INTECHOPEN.79812
M. Dascalu
{"title":"Cellular Automata and Randomization: A Structural Overview","authors":"M. Dascalu","doi":"10.5772/INTECHOPEN.79812","DOIUrl":"https://doi.org/10.5772/INTECHOPEN.79812","url":null,"abstract":"The chapter overviews the methods, algorithms, and architectures for random number generators based on cellular automata, as presented in the scientific literature. The variations in linear and two-dimensional cellular automata model and their features are discussed in relation to their applications as randomizers. Additional memory layers, functional nonuniformity in space or time, and global feedback are examples of such variations. Successful applications of cellular automata random number/signal generators (both software and hardware) reported in the scientific literature are also reviewed. The chapter includes an introductory presentation of the mathematical (ideal) model of cellular automata and its implementation as a computing model, emphasizing some important theoretical debates regarding the complexity and universality of cellular automata.","PeriodicalId":289041,"journal":{"name":"From Natural to Artificial Intelligence - Algorithms and Applications","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124666428","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}
引用次数: 1
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信