检索结果-内蒙古大学图书馆

Diagnosis of Obstructive Sleep Apnea using Formant Features of Snore Signals 10th

World Congress on Medical Physics and Biomedical Engineering

作者： Ng, Andrew K. Koh, T. S. Baey, Eugene Puvanendran, K. Nanyang Technol Univ Sch Elect & Elect Engn Nanyang Ave Singapore 639798 Singapore Respiron Inc Murrysville PA USA Singapore Gen Hosp Sleep Disorders Unit Singapore Singapore

ISBN: (纸本)9783540368397

Obstructive sleep apnea (OSA) is a sleep disordered breathing that affects about 4% of adult men and 2% of adult women in the world. It is caused by a collapse of the upper airway during sleep, which could lead to many serious consequences, such as high risk of cardiovascular morbidity and even mortality. The gold standard for OSA diagnosis is the Polysomnography (PSG), which requires patients to stay overnight in a sleep laboratory, and attached to numerous physiologic sensors. Therefore, a full PSG diagnosis can be time consuming, inconvenient, and costly. Snoring is generated by the vibrating soft tissue in the upper airway, and it is the earliest symptom of OSA. Thus, snore signals may provide an excellent framework for non-invasive diagnosis of OSA. In this paper, the use of formant features of snore signals for OSA diagnosis is presented. The raw snore signals were preprocessed using a modified Normalized Least-Mean-Square (NLMS) adaptive filter for noise cancellation, and subsequently modeled using linear predictive coding (LPC) for spectra analysis. Acoustical changes due to the collapsing upper airways can be reflected on the formant features in the frequency spectrum, which were extracted to discriminate between benign and apneic snores. Results show that the formant features of snore signals carry useful information for OSA diagnosis, and demonstrate that the use of snore signals can be a convenient, inexpensive, and reliable diagnostic approach for mass screening of OSA.

关键词： Obstructive sleep apnea Normalized least-mean-square adaptive filter linear predictive coding Formant

来源：评论

学校读者我要写书评

暂无评论

MyLipper : A Personalized System for Speech Reconstruction using Multi-View Visual Feeds 20

MyLipper : A Personalized System for Speech Reconstruction u...

引用

20th IEEE International Symposium on Multimedia (ISM)

作者： Kumar, Yaman Jain, Rohit Salik, Khwaja Mohd. Shah, Rajiv Ratn Yin, Yifang Zimmermann, Roger Adobe San Jose CA USA Univ Delhi Netaji Subhas Inst Technol MIDAS Lab New Delhi India Indraprastha Inst Informat Technol New Delhi India Natl Univ Singapore Singapore Singapore

ISBN: (纸本)9781538668573

Lipreading is the task of looking at, perceiving, and interpreting spoken symbols. It has a wide range of applications such as in surveillance, Internet telephony, speech reconstruction for silent movies and as an aid to a person with speech as well as hearing impairments. However, most of the work in lipreading literature has been limited to the classification of speech videos into text classes formed of phrases, words and sentences. Even this has been based on a highly constrained lexicon of words which, then subsequently translates to restriction on total number of classes (i.e, phrases, words and sentences) that are considered for the classification task. Recently, research has ventured into generating speech (audio) from silent video sequences. In spite of non-frontal views showing the potential of enhancing performance of speech reading and reconstruction systems, there have been no developments in using multiple camera feeds for the same. To this end, this paper presents a multi-view speech reading and reconstruction system. The major contribution of this paper is to present a model, namely MyLipper, which is a vocabulary and language agnostic and a real-time model that deals with a variety of poses of a speaker. The model leverages silent video feeds from multiple cameras recording a subject to generate intelligent speech for that speaker, thus being a personalized speech reconstruction model. It uses deep learning based STCNN+BiGRU architecture to achieve this goal. The results obtained using MyLipper show an improvement of over 20% in reconstructed speech's intelligibility (as measured by PESQ) using multiple views as compared to a single view visual feed. This confirms the importance of exploiting multiple views in building an efficient speech reconstruction system. The paper further shows the optimal placement of cameras which would lead to the maximum intelligibility of speech. Further, we demonstrate the reconstructed audios overlaid on the correspondi

关键词： Multi-layer neural network Signal reconstruction Speech synthesis linear predictive coding

来源：评论

学校读者我要写书评

暂无评论

Selected applications of LPLE in speech processing

Selected applications of LPLE in speech processing

引用

IEEE SoutheastCon 2007

作者： Schettini, Norelli Sankar, Ravi Univ S Florida Dept Elect Engn Tampa FL 33620 USA

ISBN: (纸本)9781424410286

linear Prediction with Low-frequency Emphasis (LPLE), an all-pole modeling technique which emphasizes the lower frequency range of the input signal, was described by Alku and Backstrom [1]. The method is based on first interpreting conventional linear predictive (LP) analyses of successive prediction orders with parallel structures using the concept of symmetric linear prediction. The experiments presented in this work are aimed to show that the LPLE method is well-suited for those speech processing and enhancement applications, where low-order all-pole models with improved modeling of the lowest formants are needed. This is done by replacing the LP block with a LPLE block. Distortion measures using Itakura distance and noise cancellation using a Wiener "type" filter were explored, utilizing the LPLE coefficients instead of LP coefficients.

关键词： speech analysis and processing linear predictive coding linear prediction with low-frequency emphasis

来源：评论

学校读者我要写书评

暂无评论

A Pattern Recognition Approach to Voiced-Unvoiced-Silence Classification with Applications to Speech Recognition

引用

IEEE Transactions on Acoustics, Speech, and Signal Processing 1976年第3期24卷 201-212页

作者： Atal, Bishnu S. Rabiner, Lawrence R. Bell Laboratories Murray Hill NJ 07974 United States

In speech analysis, the voiced-unvoiced decision is usually performed in conjunction with pitch analysis. The linking of voiced-unvoiced (V-UV) decision to pitch analysis not only results in unnecessary complexity, but makes it difficult to classify short speech segments which are less than a few pitch periods in duration. In this paper, we describe a pattern recognition approach for deciding whether a given segment of a speech signal should be classified as voiced speech, unvoiced speech, or silence, based on measurements made on the signal. In this method, five different measurements are made on the speech segment to be classified. The measured parameters are the zero-crossing rate, the speech energy, the correlation between adjacent speech samples, the first predictor coefficient from a 12-pole linear predictive coding (IPC) analysis, and the energy in the prediction error. The speech segment is assigned to a particular class based on a minimum-distance rule obtained under the assumption that the measured parameters are distributed according to the multidimensional Gaussian probability density function. The means and covariances for the Gaussian distribution are determined from manually classified speech data included in a training set The method has been found to provide reliable classification with speech segments as short as 10 ms and has been used for both speech analysis-synthesis and recognition applications. A simple nonlinear smoothing algorithm is described to provide a smooth 3-level contour of an utterance for use in speech recognition applications. Quantitative results and several examples illustrating the performance of the method are included in the paper. Copyright © 1976 by The Institute of Electrical and Electronics Engineers, Inc.

关键词： Pattern recognition Speech recognition Speech analysis Speech coding linear predictive coding Performance analysis Joining processes Energy measurement Density measurement Particle measurements

来源：评论

学校读者我要写书评

暂无评论

A Method for Mass Estimation of Loose Parts in Nuclear Power Plant Based on Support Vector Machine

A Method for Mass Estimation of Loose Parts in Nuclear Power...

引用

9th International Symposium on Measurement Technology and Intelligent Instruments

作者： Zheng, Huawen Cao, Yanlong Yang, Jiangxin He, Yuanfeng Zhejiang Univ Inst Mfg Engn Hangzhou 310027 Peoples R China

ISBN: (纸本)0878492739

A new method for mass estimation of loose parts in nuclear power plant (NPP) based on the support vector machine (SVM) was proposed. It includes analyses of the relationship between the impact signals' frequency spectrum and the mass of loose part, then formation of a vector consisting of linear predictive coding (LPC) parameters, which represent the shape of spectrum of impact signal. Using the vector as input data and the mass of loose part as the output data to train the SVM, the mass estimation can be done by the trained SVM model. Experimental results show that the method has higher accuracy and easier to achieve than the traditional methods. It provides a new way for mass estimation of loose part in NPP.

关键词： Loose Part Mass Estimation Support Vector Machine linear predictive coding

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Harmonic Quality of Pitch Adaptation Methods for use in Cochlear Implants 40

Evaluating the Harmonic Quality of Pitch Adaptation Methods ...

引用

40th International Conference on Telecommunications and Signal Processing (TSP)

作者： Struwe, Kevin Univ Rostock Inst Appl Microelect & Comp Engn D-18051 Rostock Germany

ISBN: (纸本)9781509039821

Some cochlear implant patients still cannot use their devices to a full extent. A limited insertion depth of the electrode array decreases the available frequency range, making speech incomprehensible. A recently proposed pitch modification method for cochlear implants aims alleviate the emerging deficiencies by modifying the pitch of an incoming signal. The pitch of the signal will be set to a fixed comfort pitch, which is the pitch of best comprehension for a given patient resulting in better speech recognition. Two approaches have been implemented to achieve this: The adaptive pitch transposition and a speech synthesis algorithm based on linear predictive coding (LPC). This paper compares the two approaches for their harmonic quality and runtime. As a result, the LPC-based approach seems better suited for cochlear implant use due to a much lower runtime as well as better harmonic quality.

关键词： Adaptivity Cochlear Implants linear predictive coding Pitch Modification

来源：评论

学校读者我要写书评

暂无评论

Acoustic Scattering of Underwater Targets

Acoustic Scattering of Underwater Targets

引用

12th Symposium on Ocean Electronics (SYMPOL)

作者： Malarkodi, A. Manamalli, D. Kavitha, G. Latha, G. Natl Inst Ocean Technol Madras 600100 Tamil Nadu India Madras Inst Technol Madras Tamil Nadu India

ISBN: (纸本)9789380095455

The objective of this paper is to provide feature extraction algorithm for underwater targets. The targets are homogeneous elastic bodies of finite dimensions. The targets considered are a brass sphere, a PVC sphere, a brass cylinder, a PVC cylinder, concrete block and MS cylinder of different dimensions. The incident acoustic signal used was a linear frequency modulated (LFM) signal of finite duration with the signal bandwidth of 40 kHz to 80 kHz. The scattered acoustic signal from the targets are recorded and processed for feature selection. The scattered signals were analysed using power spectrum analysis, linear predictive coding and Auto Regressive (AR) modelling, and its statistical features are extracted for all the targets. The nature of the backscattered signal for the underwater targets is also explained. The extracted features are passed into the feed forward neural network (FFNN) classifier. FFNN was used to identify the targets of six classes, to check the validity of extracting the feature of the targets. The result of the neural network shows that this feature extraction algorithm could enhance the fractal features of the signals and reduce the number of dimensions of the feature space and prove that it can efficiently classify underwater targets. A comprehensive study was then carried out to compare the classification performance by using these data sets in terms of performance analysis like specificity and sensitivity.

关键词： Acoustic back scattering linear predictive coding AR modelling neural network

来源：评论

学校读者我要写书评

暂无评论

A Phrase Recognizer Using Syllable-Based Acoustic Measurements

引用

IEEE Transactions on Acoustics, Speech, and Signal Processing 1978年第5期26卷 409-418页

作者： Johnson, Don H. Weinstein, Clifford J. Department of Electrical Engineering Rice University Houston TX 77001 United States MIT Lincoln Laboratories Lexington MA 02173 United States

A system for the recognition of spoken phrases is described. The recognizer assumes that the input utterance contains one of a known set of allowable phrases, which may be spoken within a longer carrier sentence. Analysis is performed on a syllable-by-syllable basis with only the strong syllables considered in the recognition process. Each strong syllable is represented in terms of a set of distinguishing acoustic measurements taken at time points in and around the syllable nucleus. Phrases are represented as sequences of strong syllables. All parameters used in recognition are derived from LPC coefficients. Input speech is limited to 3.3 kHz upper frequency. Recognition is completed within 1–3 s after the utterance is spoken. An interactive training facility allows flexible composition of key phrase sets. Testing was performed for a number of phrase sets each containing ten or fewer phrases, and included equal numbers of talkers used in training and talkers not used in training. Average phrase recognition accuracy was 95 percent when parameters were derived from unquantized (i.e., 16-bit) LPC coefficients and 90 percent when the LPC coefficients were transmitted to the recognizer across the ARPA network at 3500 bits/s. The recognizer has been incorporated into a user interface system where the parameters required to set up a point-to-point ARPANET voice connection can be established remotely by voice. © 1978 IEEE.

关键词： Acoustic measurements Speech recognition linear predictive coding Bandwidth User interfaces ARPANET Speech analysis Performance analysis Gold Frequency

来源：评论

学校读者我要写书评

暂无评论

Robust speaker identification system using multi-band dominant features with empirical mode decomposition

Robust speaker identification system using multi-band domina...

引用

10th International Conference on Computer and Information Technology

作者： Molla, Md. Khademul Islam Hirose, Keikichi Minematsu, Nobutaki Univ Tokyo Grad Sch Informat Sci & Technol Bunkyo Ku 7-3-1 Hongo Tokyo 1130033 Japan Univ Tokyo Grad Sch Frontier Sci Tokyo Japan

ISBN: (纸本)9781424415502

This paper presents a text independent speaker identification system using multi-band features with artificial neural network. linear predictive cepstrum coefficients (LPCCs) computed from sub-band signals with higher order statistics (HOS) are employed as the main features to represent the speaker characteristics. The multi-band representation of the speech signal is implemented by empirical mode decomposition (EMD). Dominant feature vectors are derived by applying principal component analysis (PCA) on LPCC space computed from the speech signal. The experimental results show that the proposed system improves the speaker identification performance. The efficiency is also compared for different features with noisy speech signals.

关键词： speaker recognition bandpass filtering higher order statistics linear predictive coding cepstral analysis

来源：评论

学校读者我要写书评

暂无评论

Classification of Healthy and Pathologic Lung Sounds Recorded with Electronic Auscultation 23

Classification of Healthy and Pathologic Lung Sounds Recorde...

引用

23nd Signal Processing and Communications Applications Conference (SIU)

作者： Aras, Selim Gangal, Ali Bulbul, Yilmaz Karadeniz Tech Univ Elekt Elekt Muhendisligi Bolumu Trabzon Turkey Karadeniz Tech Univ Gogus Hastaliklari Anabilim Dali Trabzon Turkey

ISBN: (纸本)9781467373869

In this paper, lung sounds recorded by electronic auscultation, were classified as healthy and pathological. linear predictive coding coefficients, Mel Frequency Cepstrum Coefficients mean and standard deviation were used as features. Records are consists of two data sets containing different respiratory cycle, k-Nearest Neighbor classification algorithm used and the performance obtained were discussed in the conclusion to the case of using different data sets and different attributes.

关键词： Electronic Auscultation Lung Sounds Mel Frequency Cepstrum Coefficients linear predictive 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：