检索结果-内蒙古大学图书馆

Simulation and overall comparative evaluation of performance between different techniques for high band feature extraction based on artificial bandwidth extension of speech over proposed global system for mobile full rate narrow band coder

引用

INTERNATIONAL JOURNAL OF SPEECH TECHNOLOGY 2016年第4期19卷 881-893页

作者： Bhatt, Ninad S. CK Pithawalla Coll Engn & Technol Dept Elect & Commun Engn Surat Gujarat India

This paper addresses a novel approach to investigate, study and simulate computation of high band (HB) feature extraction based on linear predictive coding (LPC) and mel frequency cepstral coefficient (MFCC) techniques. Further, HB features are embedded into encoded bitstream of proposed global system for mobile (GSM) full rate (FR) 06.10 coder using joint source coding and data hiding before being transmitted to receiving terminal. At receiver, HB features are extracted to reproduce HB portion of speech and for the same different extension of excitation techniques are applied and their results evaluated in terms of quality (intelligibility and naturalness) and bandwidth. MATLAB based e-test bench is created for implementing the proposed artificial bandwidth extension (ABE) coder following series of simulations, that are carried out to discover and gain insight about the performance of it using subjective [mean opinion score (MOS)] and objective [perceptual evaluation of speech quality (PESQ)] analysis. The results obtained for both the analyses advocate that proposed ABE coder outperforms proposed GSM FR NB (legacy GSM FR) coder. While the fact remains that, compared to LPC based parameterizations over ABE coder, MFCC parameterization results in higher speech intelligibility which is evident from obtained slightly better PESQ and MOS scores.

关键词： GSM full rate coder Artificial bandwidth extension linear predictive coding Mel frequency cepstral coefficients Subjective analysis Objective analysis

来源：评论

学校读者我要写书评

暂无评论

Voiced-Unvoiced Classification of Speech Using a Neural Network Trained with LPC Coefficients

Voiced-Unvoiced Classification of Speech Using a Neural Netw...

引用

International Conference on Control, Artificial Intelligence, Robotics & Optimization (ICCAIRO)

作者： Kevin Struwe Institute of Applied Microelectronics and Computer Engineering University of Rostock Rostock Germany

ISBN: (纸本)9781509065370

Voiced-Unvoiced classification (V-UV) is a well understood but still not perfectly solved problem. It tackles the problem of determining whether a signal frame contains harmonic content or not. This paper presents a new approach to this problem using a conventional multi-layer perceptron neural network trained with linear predictive coding (LPC) coefficients. LPC is a method that results in a number of coefficients that can be transformed to the envelope of the spectrum of the input frame. As a spectrum is suitable for determining the harmonic content, so are the LPC-coefficients. The proposed neural network works reasonably well compared to other approaches and has been evaluated on a small dataset of 4 different speakers.

关键词： Speech Training Neural networks linear predictive coding Harmonic analysis Cochlear implants

来源：评论

学校读者我要写书评

暂无评论

Enhanced Spin-Down Diagnostics for Nondestructive Evaluation of High-Value Systems 34th

Enhanced Spin-Down Diagnostics for Nondestructive Evaluation...

引用

34th IMAC Conference and Exposition on Structural Dynamics

作者： Sehloff, David Shurtleff, Clark Pribe, Josh Haynes, Colin Heit, John Washington Univ Dept Elect & Syst Engn St Louis MO USA Univ Penn Dept Mat Sci & Engn 3231 Walnut St Philadelphia PA 19104 USA Missouri Univ Sci & Technol Dept Mech & Aerosp Engn Rolla MO USA Los Alamos Natl Lab Weap Engn Los Alamos NM 87544 USA

ISBN: (纸本)9783319300849;9783319300832

The nature of some high-value systems requires that damage be detected without disassembly of the test article. Spin-down testing, one such nondestructive evaluation method, involves spinning a test article and observing its angular deceleration. An increase in angular deceleration compared to an identical test of a healthy system indicates damage has occurred. However, current testing is limited, providing only a binary result of "damaged" or "undamaged". More sophisticated techniques are required to identify the location, extent, and type of damage. To achieve this, non-contact and surface-mounted sensors were used to monitor the test article in this experiment. A spin-down unit was used to test both a healthy specimen and a specimen with simulated damage. The signals from each sensor were compared across tests. Correlation of anomalous signals with rotational position and multi-sensor triangulation techniques were used to localize damage. Analysis of the frequency content and amplitude of output signals allowed for a degree of characterization of the damage. Through these techniques, spin-down testing was enhanced from a binary detector to a more thorough testing method giving detailed information about the type and location of damage.

关键词： Spin-down testing Rotating system Nondestructive evaluation Acoustic emissions sensing linear predictive coding

来源：评论

学校读者我要写书评

暂无评论

Speech Recognition using Support Vector Machines 10

Speech Recognition using Support Vector Machines

引用

10th IEEE International Conference on Application of Information and Communication Technologies (AICT)

作者： Aida-zade, Kamil Xocayev, Anar Rustamov, Samir Azerbaijan Natl Acad Sci Inst Control Syst Baku Azerbaijan Qafqaz Univ Comp Engn Baku Azerbaijan ADA Univ Azerbaijan Natl Acad Sci Inst Control Syst Baku Azerbaijan

ISBN: (纸本)9781509018413

In this article we applied Support Vector Machines to acoustic model of Speech Recognition System based on MFCC and LPC features for Azerbaijani DataSet. This DataSet has been used for speech recognition by Multilayer Artificial Neural Network and achieved some results. The main goal of this work is applying SVM techniques to the Azerbaijan Speech Recognition System. The variety of results of SVM with different Kernel functions is analyzed in the training process. It is shown that SVM with radial basis and polynomial kernels give better recognition results that Multilayer Artificial Neural Network.

关键词： Speech Recognition Feature Extraction Support Vector Machines linear predictive coding Mel Frequency Cepstral Coefficients

来源：评论

学校读者我要写书评

暂无评论

Temporal Compression in Wireless Sensor Networks using Compressive Sensing and ARMA modeling 2

Temporal Compression in Wireless Sensor Networks using Compr...

引用

2nd International Conference on Advances in Computing, Communication, and Automation (ICACCA) (Fall)

作者： Thapliyal, Ashish Kumar, Rajender Natl Inst Technol Kurukshetra Dept Elect & Commun Engn Kurukshetra Haryana India

ISBN: (纸本)9781509034802

In this paper a new method is proposed which reduce the redundancy of data transmission in Wireless Sensor Network (WSN). In a dense environment of sensors, energy efficiency is key factor for prolonged battery life. Here in this paper temporal redundancy of sensor node is reduced using hybrid of two methods, one is compressive sensing using Discrete Cosine Transform (DCT) and other one is linear predictive coding (LPC). Given method is not suitable for real time data monitoring rather it is better for delay tolerant services as it require processing time before transmission. Here it is assumed that data monitored by sensors is piecewise linear. The relevancy in temporal data exploited here for data compression. First data monitored from each node for a long enough span of time which is further segmented according to their linearity. As compressive sensing compress the data and ARMA also use only few of the transmission bits, combination of both provide satisfactory compression of stored data. The segmented data used as input for compression and further processed to sink node. Result shows that this scheme provide satisfactory compression rate of monitored data.

关键词： wireless sensor network Discrete cosine transform linear predictive coding Compressive Sensing, auto regressive moving average

来源：评论

学校读者我要写书评

暂无评论

Study of Vocal Tract Shape Estimation Techniques for Children 7

Study of Vocal Tract Shape Estimation Techniques for Childre...

引用

7th International Conference on Communication, Computing and Virtualization (ICCCV)

作者： Veena, S. Wankhede, Nilashree S. Shah, Milind S. Fr C Rodrigues Inst Technol Dept Electon & Telecommun Engn Sect 9A Mumbai 400703 Maharashtra India

Accurate depiction of the vocal tract shape is essential for development of speech training aids for hearing impaired. Speech therapists have concluded from their research that if speech disorders are detected at an early stage then the rectification of those becomes faster and to a great accuracy. In case of adults, the vocal tract shape estimation can be performed by using techniques like X-Ray, MRI or using articulatory analysis by synthesis. Due to certain difficulties present in the methods mentioned like radiation effect and loud sound impulses produced by rapid switching of magnetic field are not considered suitable for children. Thus there is lack of availability of vocal tract shape data for children due to inability to use direct estimation methods for children. So it becomes necessary to carry out comparative study of vocal tract shape estimation techniques of children using indirect vocal tract shape estimation techniques. This paper aims to make available a considerable amount of data to researchers for study towards children's vocal tract shape using implemented techniques. The final objective of research work is to perform a detailed study on techniques available for vocal tract shape estimation, to implement and further compare the covariance and lattice methods for children using MATLAB software. Currently, the vocal tract shape estimation based on autocorrelation method is implemented and the results obtained are presented. (C) 2016 The Authors. Published by Elsevier B.V.

关键词： Vocal tract shape estimation linear predictive coding Speech training hearing impaired

来源：评论

学校读者我要写书评

暂无评论

LOCALIZATION OF ACOUSTIC SOURCE ON SOLIDS: A linear predictive coding BASED ALGORITHM FOR LOCATION TEMPLATE MATCHING

LOCALIZATION OF ACOUSTIC SOURCE ON SOLIDS: A LINEAR PREDICTI...

引用

2010 IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Yap, XueXin Khong, Andy W. H. Gan, Woon-Seng Nanyang Technol Univ Singapore Singapore

ISBN: (纸本)9781424442966

Location template matching (LTM) is a source localization technique in solids that is robust to dispersion and multipath. This is possible since LTM compares the input with a database of signals made at known locations. With this in place, it is possible to employ LTM in situations where the surface of interest takes an irregular shape. However, one of the existing LTM approaches uses cross-correlation to compare the input and the database. It should be noted that if any two of the known locations stored in the database are too close, the cross-correlation method may have difficulties differentiating between signals generated from the neighboring points. To address this, we propose an algorithm which employs the linear predictive coding (LPC) that takes into account the dominant frequencies of a received signal. Using this approach, we show that the proposed algorithm is able to improve LTM's source localization accuracy under a real environment in the context of source localization for a touch interface.

关键词： user interfaces correlation linear predictive coding location template matching

来源：评论

学校读者我要写书评

暂无评论

Automatic Characterization and Detection of Behavioral Patterns Using linear predictive coding of Accelerometer Sensor Data

Automatic Characterization and Detection of Behavioral Patte...

引用

32nd Annual International Conference of the IEEE Engineering-in-Medicine-and-Biology-Society (EMBC 10)

作者： Min, Cheol-Hong Tewfik, Ahmed H. Univ Minnesota Twin Cities Dept Elect & Comp Engn Minneapolis MN 55455 USA

ISBN: (纸本)9781424441242

In this study, we target to automatically detect behavioral patterns of patients with autism. Many stereotypical behavioral patterns may hinder their learning ability as a child and patterns such as self-injurious behaviors (SIB) can lead to critical damages or wounds as they tend to repeatedly harm one single location. Our custom designed accelerometer based wearable sensor can be placed at various locations of the body to detect stereotypical self-stimulatory behaviors (stereotypy) and self-injurious behaviors of patients with Autism Spectrum Disorder (ASD). A microphone was used to record sounds so that we may understand the surrounding environment and video provided ground truth for analysis. The analysis was done on four children diagnosed with ASD who showed repeated self-stimulatory behaviors that involve part of the body such as flapping arms, body rocking and self-injurious behaviors such as punching their face, or hitting their legs. The goal of this study is to devise novel algorithms to detect these events and open possibility for design of intervention methods. In this paper, we have shown time domain pattern matching with linear predictive coding (LPC) of data to design detection and classification of these ASD behavioral events. We observe clusters of pole locations from LPC roots to select candidates and apply pattern matching for classification. We also show novel event detection using online dictionary update method. We show that our proposed method achieves recall rate of 95.5% for SIB, 93.5% for flapping, and 95.5% for rocking which is an increase of approximately 5% compared to flapping events detected by using wrist worn sensors in our previous study.

关键词： ASD accelerometer accelerometers autism spectrum disorder behavioral event classification behavioral event detection behavioral patterns biomedical measurement children encoding linear predictive coding medical disorders medical signal processing microphone microphones online dictionary update method paediatrics pattern matching psychology signal classification stereotypical self-stimulatory behaviors time domain pattern matching wearable sensor wounds

来源：评论

学校读者我要写书评

暂无评论

Study of Vocal Tract Shape Estimation Techniques for Children

引用

Procedia Computer Science 2016年 79卷 270-277页

作者： Veena S. Nilashree S. Wankhede Milind S. Shah Department of Electonics and Telecommunication Engineering Fr. C. Rodrigues Institute of Technology Sector 9A Vashi Navi Mumbai Maharashtra 400703 India

关键词： Vocal tract shape estimation linear predictive coding Speech training hearing impaired

来源：评论

学校读者我要写书评

暂无评论

Modeling of voiced and unvoiced speech signals using fractional calculus

Modeling of voiced and unvoiced speech signals using fractio...

引用

International Conference on Next Generation Intelligent Systems (ICNGIS)

作者： Anju Abraham A Harsha Department of Electronics and Communication Engg. Rajagiri School of Engineering and Technology Kochi India

ISBN: (纸本)9781509008711

In this paper, a novel approach for modeling voiced and unvoiced speech signal using fractional calculus is presented. In this work a comparative study between linear predictive coding (LPC) and Fractional Fourier Transform is done. Based on this the voiced and unvoiced speech signal can be modeled accurately. Fractional calculus method requires smaller number of model parameters, and it is superior to the LPC approach in capturing the details of the modeled signal.

关键词： Speech Fourier transforms linear predictive coding Speech processing Fractional calculus Speech coding

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：