Pub Date : 2021-04-09DOI: 10.5013/IJSSST.A.22.01.09
Tristan Nolan, Enda Fallon, Paul Connolly, Kieran Flanagan
- This research proposes a method which evaluates a real-world data analytics business process to identify key performance variables for the manual business process. Once complete, we incorporate these finding to an unsupervised machine learning algorithm to allow for tuning of the outputs. Experiments show that using this approach can reduce the overall number of undesired outputs, giving an overall higher effectiveness for the ML system in a real-world application. The proposed method offers consistency while providing an organization the option of focusing resources on high value activities.
{"title":"Business Process Automation: Automating the Analysis of Anomaly Data","authors":"Tristan Nolan, Enda Fallon, Paul Connolly, Kieran Flanagan","doi":"10.5013/IJSSST.A.22.01.09","DOIUrl":"https://doi.org/10.5013/IJSSST.A.22.01.09","url":null,"abstract":"- This research proposes a method which evaluates a real-world data analytics business process to identify key performance variables for the manual business process. Once complete, we incorporate these finding to an unsupervised machine learning algorithm to allow for tuning of the outputs. Experiments show that using this approach can reduce the overall number of undesired outputs, giving an overall higher effectiveness for the ML system in a real-world application. The proposed method offers consistency while providing an organization the option of focusing resources on high value activities.","PeriodicalId":14286,"journal":{"name":"International journal of simulation: systems, science & technology","volume":"62 3 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79671764","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 : 2021-04-04DOI: 10.5013/IJSSST.A.22.01.04
Pravir Malik
This paper suggests that a symmetrical multi-layered model of light is the generator of increasingly complex computationalstrata. The light-based symmetry being quaternary-based, is envisioned to generate similar quaternary-based strata such as the electromagnetic field, quantum particles, atoms, and cells. But such generation occurs through the device of quanta, which is seen to be a bridge mechanism between layers of light. Such strata, afforded stability because the implicit fourfoldness in light seeks integrality even when projected explicitly, allows subsequent phenomenon such as memory and the implementation of universal functionality to arise. Because memory and universal functionality can be implemented in any of the quaternary-based emergent strata through the creation of logical gates leveraging strata-specific mechanisms, such strata become computational-strata. A different object of computation, an innate creativity, becomes apparent when one considers the vast array of unique functionality that is emergent in any layer of computational-strata. Further, the generation of such computational-strata has profound implications on quantum computation, genetics, artificial intelligence, and transhumanism.
{"title":"The Emergence of Quaternary-Based Computational-Strata from a Symmetrical Multi-Layered Model of Light","authors":"Pravir Malik","doi":"10.5013/IJSSST.A.22.01.04","DOIUrl":"https://doi.org/10.5013/IJSSST.A.22.01.04","url":null,"abstract":"This paper suggests that a symmetrical multi-layered model of light is the generator of increasingly complex computationalstrata. The light-based symmetry being quaternary-based, is envisioned to generate similar quaternary-based strata such as the electromagnetic field, quantum particles, atoms, and cells. But such generation occurs through the device of quanta, which is seen to be a bridge mechanism between layers of light. Such strata, afforded stability because the implicit fourfoldness in light seeks integrality even when projected explicitly, allows subsequent phenomenon such as memory and the implementation of universal functionality to arise. Because memory and universal functionality can be implemented in any of the quaternary-based emergent strata through the creation of logical gates leveraging strata-specific mechanisms, such strata become computational-strata. A different object of computation, an innate creativity, becomes apparent when one considers the vast array of unique functionality that is emergent in any layer of computational-strata. Further, the generation of such computational-strata has profound implications on quantum computation, genetics, artificial intelligence, and transhumanism.","PeriodicalId":14286,"journal":{"name":"International journal of simulation: systems, science & technology","volume":"257 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77092124","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 : 2021-04-04DOI: 10.5013/IJSSST.A.22.01.07
Eirik Haraldsen, Karl Østrådt, R. Davidrajuh
{"title":"Understanding the Importance of Efficient Visitor Flow Within Tokyo Skytree","authors":"Eirik Haraldsen, Karl Østrådt, R. Davidrajuh","doi":"10.5013/IJSSST.A.22.01.07","DOIUrl":"https://doi.org/10.5013/IJSSST.A.22.01.07","url":null,"abstract":"","PeriodicalId":14286,"journal":{"name":"International journal of simulation: systems, science & technology","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81985298","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 : 2020-12-30DOI: 10.5013/ijssst.a.16.06.08
M. Asvial
An increasing needs of a high bit rate transmission systems encourage the communication engineers to design a better system. In practical, a 40 Gbps rate of transmission can only be achieved in a fiber optic system. Although this performance can be achieved through this media, the disturbances such as dispersion and non linearity which can be manifested into a pulse broadening may occur during the transmission system. Since this phenomenonis caused by the Group Velocity Dispersion (GVD) in a high bit rate fiber optic, a careful consideration on the effectiveness of the systems is needed. A numerical approach in this paper used a novel analysis method of high order NLSE with a Split Step Fourier Method. The aims of this proposed model is to find a suitable value of the dispersion constants in terms of and which are assumed to be a part of second and third order dispersion respectively. To reduce the effect of pulse broadening, this paper proposed an novel approach through the value of pulse broadening ratio and intensity. Consequently, it is found that a negative pre-chirping in the averaged value of 1.8944 and C=-2 have the best result among others in a Gaussian signal simulation.
{"title":"Split Step Fourier Method Application, Reducing Pulse Broadening Effect for a Single Mode Optical Fiber","authors":"M. Asvial","doi":"10.5013/ijssst.a.16.06.08","DOIUrl":"https://doi.org/10.5013/ijssst.a.16.06.08","url":null,"abstract":"An increasing needs of a high bit rate transmission systems encourage the communication engineers to design a better system. In practical, a 40 Gbps rate of transmission can only be achieved in a fiber optic system. Although this performance can be achieved through this media, the disturbances such as dispersion and non linearity which can be manifested into a pulse broadening may occur during the transmission system. Since this phenomenonis caused by the Group Velocity Dispersion (GVD) in a high bit rate fiber optic, a careful consideration on the effectiveness of the systems is needed. A numerical approach in this paper used a novel analysis method of high order NLSE with a Split Step Fourier Method. The aims of this proposed model is to find a suitable value of the dispersion constants in terms of and which are assumed to be a part of second and third order dispersion respectively. To reduce the effect of pulse broadening, this paper proposed an novel approach through the value of pulse broadening ratio and intensity. Consequently, it is found that a negative pre-chirping in the averaged value of 1.8944 and C=-2 have the best result among others in a Gaussian signal simulation.","PeriodicalId":14286,"journal":{"name":"International journal of simulation: systems, science & technology","volume":"36 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73041783","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 : 2020-12-30DOI: 10.5013/IJSSST.A.21.04.13
S. Thongkrairat, V. Chutchavong
Many optimisation techniques have recently been developed. Several mimic natural activity or another theory, such as the Grey Wolf Optimiser, which emulates wolf hunting mechanisms to find a global minimum, and Particle Swarm Optimisation, which uses birds’ flocking behaviour to avoid each local minimum. Each developed algorithm uses guidelines to improve its mimicry and reach its goal. This work proposes the pivot optimiser, a new evolution optimisation algorithm inspired by the multidimensional geometric method to create a unique evolution in each generation. The goal of this imitation is to make an algorithm suitable for a multi-situation problem with a stable result. The results show that the pivot optimiser outperformed on competitive problems compared with other competitive optimisers. Keywordsoptimisation, algorithm, swarm intelligence, geometric, GWO, PSO
{"title":"A Novel Evolution Optimization Algorithm Using a Multidimensional Geometric Method: Pivot Optimiser","authors":"S. Thongkrairat, V. Chutchavong","doi":"10.5013/IJSSST.A.21.04.13","DOIUrl":"https://doi.org/10.5013/IJSSST.A.21.04.13","url":null,"abstract":"Many optimisation techniques have recently been developed. Several mimic natural activity or another theory, such as the Grey Wolf Optimiser, which emulates wolf hunting mechanisms to find a global minimum, and Particle Swarm Optimisation, which uses birds’ flocking behaviour to avoid each local minimum. Each developed algorithm uses guidelines to improve its mimicry and reach its goal. This work proposes the pivot optimiser, a new evolution optimisation algorithm inspired by the multidimensional geometric method to create a unique evolution in each generation. The goal of this imitation is to make an algorithm suitable for a multi-situation problem with a stable result. The results show that the pivot optimiser outperformed on competitive problems compared with other competitive optimisers. Keywordsoptimisation, algorithm, swarm intelligence, geometric, GWO, PSO","PeriodicalId":14286,"journal":{"name":"International journal of simulation: systems, science & technology","volume":"41 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74399747","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 : 2020-12-30DOI: 10.5013/ijssst.a.21.01.09
M. Shkoukani, A. Altamimi
{"title":"Graph Database Security: Blockchain Solution and Open Challenges","authors":"M. Shkoukani, A. Altamimi","doi":"10.5013/ijssst.a.21.01.09","DOIUrl":"https://doi.org/10.5013/ijssst.a.21.01.09","url":null,"abstract":"","PeriodicalId":14286,"journal":{"name":"International journal of simulation: systems, science & technology","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78284786","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 : 2020-12-30DOI: 10.5013/ijssst.a.15.06.12
P. Sallis, C. Dannheim, Christian Icking, M. Maeder
The general area of research described here relates in part to computational pattern recognition and image processing. More specifically however, it relates to image recognition of amorphous objects, which due to their ill-defined shape, are difficult to identify. In particular, the focus for the research relates to vehicle mounted weather condition sensors that are operated during journeys on public roads and how these sensors can be used to gather sufficiently comprehensive data for algorithmic analysis such that timely and accurate results can be obtained. In large part this work has been conducted together with researchers in the Connected Car Project, based at BMW in Munich, Germany. The principal research question is how accurately data can be obtained from vehicle-mounted cameras and LIDAR (Light Detection and Recognition) to identify ill-formed objects such as fog, low cloud and particulate matter such as smoke. The operation of the sensor equipment, building of a data matrix for analysis, algorithm design and the results from experiments with these instruments is the context for this paper. Keywords-Image Processing, Pattern Recognition, Algortihm Design, Air Pollution Detection, Fog Detection, Weather Detection, Remote Sensing, LIDAR, Colaborative Driver Assistant Functions, Spatial Resolution, Air Pollution Forecasting Services.
这里描述的一般研究领域部分涉及计算模式识别和图像处理。然而，更具体地说，它涉及到无定形物体的图像识别，由于其形状不明确，难以识别。特别是，研究的重点涉及在公共道路上行驶时运行的车载天气状况传感器，以及如何使用这些传感器收集足够全面的数据进行算法分析，从而获得及时准确的结果。在很大程度上，这项工作是与位于德国慕尼黑的宝马公司(BMW)互联汽车项目(Connected Car Project)的研究人员共同完成的。主要的研究问题是如何准确地从车载摄像头和激光雷达(光探测和识别)中获得数据，以识别雾、低云和烟雾等颗粒物质等形状不良的物体。本文的背景是传感器设备的运行、分析数据矩阵的建立、算法设计以及这些仪器的实验结果。关键词:图像处理，模式识别，算法设计，空气污染检测，雾检测，天气检测，遥感，激光雷达，协同驾驶辅助功能，空间分辨率，空气污染预报服务。
{"title":"Instrumentation and Algorithms for the Identification of Ill-formed Objects","authors":"P. Sallis, C. Dannheim, Christian Icking, M. Maeder","doi":"10.5013/ijssst.a.15.06.12","DOIUrl":"https://doi.org/10.5013/ijssst.a.15.06.12","url":null,"abstract":"The general area of research described here relates in part to computational pattern recognition and image processing. More specifically however, it relates to image recognition of amorphous objects, which due to their ill-defined shape, are difficult to identify. In particular, the focus for the research relates to vehicle mounted weather condition sensors that are operated during journeys on public roads and how these sensors can be used to gather sufficiently comprehensive data for algorithmic analysis such that timely and accurate results can be obtained. In large part this work has been conducted together with researchers in the Connected Car Project, based at BMW in Munich, Germany. The principal research question is how accurately data can be obtained from vehicle-mounted cameras and LIDAR (Light Detection and Recognition) to identify ill-formed objects such as fog, low cloud and particulate matter such as smoke. The operation of the sensor equipment, building of a data matrix for analysis, algorithm design and the results from experiments with these instruments is the context for this paper. Keywords-Image Processing, Pattern Recognition, Algortihm Design, Air Pollution Detection, Fog Detection, Weather Detection, Remote Sensing, LIDAR, Colaborative Driver Assistant Functions, Spatial Resolution, Air Pollution Forecasting Services.","PeriodicalId":14286,"journal":{"name":"International journal of simulation: systems, science & technology","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76647862","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 : 2020-12-30DOI: 10.5013/ijssst.a.21.01.05
B. Barokah, S. Semin, B. Cahyono, B. Sampurno
{"title":"Design of New Fin Baffle Shell and Tube Heat Exchanger for Heating of Biodiesel Fuel Based on Simulation","authors":"B. Barokah, S. Semin, B. Cahyono, B. Sampurno","doi":"10.5013/ijssst.a.21.01.05","DOIUrl":"https://doi.org/10.5013/ijssst.a.21.01.05","url":null,"abstract":"","PeriodicalId":14286,"journal":{"name":"International journal of simulation: systems, science & technology","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76945648","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 : 2020-12-30DOI: 10.5013/ijssst.a.15.06.07
A. Shah, Yuki Ishikawa, Suguru Odakura, N. Kakimoto
Renewable energy resources such as photovoltaic (PV) or wind energy are essential to endure an approaching energy crisis in the near future. However, an effective idea of control needs to be well structured in advance so that the accumulated energy generated from these resources can be managed in an appropriate way. In this paper, a numerical model that computes an optimized value of energy consumption based on weekly forecast has been performed in order to provide stable energy that is highly uninfluenced by the fluctuating weather. A smart energy control method for Home Energy Management System (HEMS) that is capable of increasing the energy consumption in sunny days while maintaining a minimum consistent value of energy in bad weather conditions is proposed. The simulated system succeeded in supplying at least 10 Ah of energy to the load in most cases during the rainy/cloudy days. Plus, the number of insufficient day, (NID) were reduced significantly to 0 day in most years from the year 2000 to 2010 when the battery capacity was further expanded from 30 to 35 Ah. Keywords-Power Control, Lithium-ion Battery, Energy Management, Photovoltaic.
{"title":"Numerical Model of Energy Control for Lithium-Ion Batteries Based on PV System","authors":"A. Shah, Yuki Ishikawa, Suguru Odakura, N. Kakimoto","doi":"10.5013/ijssst.a.15.06.07","DOIUrl":"https://doi.org/10.5013/ijssst.a.15.06.07","url":null,"abstract":"Renewable energy resources such as photovoltaic (PV) or wind energy are essential to endure an approaching energy crisis in the near future. However, an effective idea of control needs to be well structured in advance so that the accumulated energy generated from these resources can be managed in an appropriate way. In this paper, a numerical model that computes an optimized value of energy consumption based on weekly forecast has been performed in order to provide stable energy that is highly uninfluenced by the fluctuating weather. A smart energy control method for Home Energy Management System (HEMS) that is capable of increasing the energy consumption in sunny days while maintaining a minimum consistent value of energy in bad weather conditions is proposed. The simulated system succeeded in supplying at least 10 Ah of energy to the load in most cases during the rainy/cloudy days. Plus, the number of insufficient day, (NID) were reduced significantly to 0 day in most years from the year 2000 to 2010 when the battery capacity was further expanded from 30 to 35 Ah. Keywords-Power Control, Lithium-ion Battery, Energy Management, Photovoltaic.","PeriodicalId":14286,"journal":{"name":"International journal of simulation: systems, science & technology","volume":"53 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76300495","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 : 2020-12-30DOI: 10.5013/ijssst.a.15.06.05
He Pan, Yangjie Wei, Nan Guan, Yi Wang
Voice conversion system modifies a speaker’s voice to be perceived as another speaker uttered, and now it is widely used in many real applications. However, most research only focuses on one aspect performance of voice conversion system, rare theoretical analysis and experimental comparison on the whole source-target speaker voice conversion process has been introduced. Therefore, in this paper, a comprehensive analysis on source-target speaker voice conversion is conducted based on three key steps, including acoustic features selection and extraction, voice conversion model construction, and target speech synthesis, and a complete and optimal source-target speaker voice conversion is proposed. First, a simple and direct serial feature fusion form consisting of prosodic feature, spectrum parameter and spectral envelope characteristic, is proposed. Then, to void the discontinuity and spectrum distortion of a converted speech, D_GMM (Dynamic Gaussian Mixture Model) considering dynamic information between frames is presented. Subsequently, for speech synthesis, STRAIGHT algorithm synthesizer with feature combination is modified. Finally, the objective contrast experiment shows that our new source-target voice conversion process achieves better performance than the conventional methods. In addition, both objective evaluation (speaker recognition system) and subjective evaluation are used to evaluate the quality of converted speech, and experimental result shows that the converted speech has higher target speaker individuality and speech quality. Keywords-Voice Conversion, Serial Feature Fusion, D_GMM, STRAIGHT Synthesis, Speaker Recognition. I.! INTRODUCTION Source-target speaker voice conversion is a technique that modifies a source speaker’s speech to make it sound like that uttered by a target speaker without changing the speech content [1]. In the last two decades, much attention has been attracted to it due to its wide potential application areas, such as dubbing in films, restoring damaged voice and disguising personal voice [2]. Normally, source-target speaker voice conversion consists of three key steps: (1) selection and extraction of representative acoustic features; (2) construction of voice conversion model; (3) synthesis of the target speech. Firstly, acoustic features selection and extraction is to select acoustic features those can represent a speaker’s individual identity, and extract them correctly. Many researchers have proved that prosodic features, formant frequency and spectral parameters are the most important features used in real applications [3-4]. However, most study only focus on one or two of them to represent a speaker’s individual identity [5-6], that causing the covered acoustic features to be incomprehensive and the final synthesized speech to be inaccurate. Secondly, a voice conversion model consists of a sequence of mapping rules between the source speaker and the target speaker. Gaussian mixture model, which convert
{"title":"Comprehensive Source-Target Speaker Voice Conversion Analysis","authors":"He Pan, Yangjie Wei, Nan Guan, Yi Wang","doi":"10.5013/ijssst.a.15.06.05","DOIUrl":"https://doi.org/10.5013/ijssst.a.15.06.05","url":null,"abstract":"Voice conversion system modifies a speaker’s voice to be perceived as another speaker uttered, and now it is widely used in many real applications. However, most research only focuses on one aspect performance of voice conversion system, rare theoretical analysis and experimental comparison on the whole source-target speaker voice conversion process has been introduced. Therefore, in this paper, a comprehensive analysis on source-target speaker voice conversion is conducted based on three key steps, including acoustic features selection and extraction, voice conversion model construction, and target speech synthesis, and a complete and optimal source-target speaker voice conversion is proposed. First, a simple and direct serial feature fusion form consisting of prosodic feature, spectrum parameter and spectral envelope characteristic, is proposed. Then, to void the discontinuity and spectrum distortion of a converted speech, D_GMM (Dynamic Gaussian Mixture Model) considering dynamic information between frames is presented. Subsequently, for speech synthesis, STRAIGHT algorithm synthesizer with feature combination is modified. Finally, the objective contrast experiment shows that our new source-target voice conversion process achieves better performance than the conventional methods. In addition, both objective evaluation (speaker recognition system) and subjective evaluation are used to evaluate the quality of converted speech, and experimental result shows that the converted speech has higher target speaker individuality and speech quality. Keywords-Voice Conversion, Serial Feature Fusion, D_GMM, STRAIGHT Synthesis, Speaker Recognition. I.! INTRODUCTION Source-target speaker voice conversion is a technique that modifies a source speaker’s speech to make it sound like that uttered by a target speaker without changing the speech content [1]. In the last two decades, much attention has been attracted to it due to its wide potential application areas, such as dubbing in films, restoring damaged voice and disguising personal voice [2]. Normally, source-target speaker voice conversion consists of three key steps: (1) selection and extraction of representative acoustic features; (2) construction of voice conversion model; (3) synthesis of the target speech. Firstly, acoustic features selection and extraction is to select acoustic features those can represent a speaker’s individual identity, and extract them correctly. Many researchers have proved that prosodic features, formant frequency and spectral parameters are the most important features used in real applications [3-4]. However, most study only focus on one or two of them to represent a speaker’s individual identity [5-6], that causing the covered acoustic features to be incomprehensive and the final synthesized speech to be inaccurate. Secondly, a voice conversion model consists of a sequence of mapping rules between the source speaker and the target speaker. Gaussian mixture model, which convert","PeriodicalId":14286,"journal":{"name":"International journal of simulation: systems, science & technology","volume":"87 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75987223","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：