 Abstract—One of the major issues when transforming a voice using the PSOLA algorithm is to be able to accurately find the values for the signal modification parameters (α, β and γ) that allow us to transform the source signal into the target signal. In this paper, we propose a way to determine these parameters on the basis of a study of their influence on some speech acoustic descriptors. We are then able to deduce the relationship between each transformation parameter and the feature parameters of the voice. The obtained results are acceptable and allowed us to sort the vocal features in ascending order of transformation complexity.

               R=  

인간의 동작 인식은 건강관리, 상황기반 응용 등 실제적인 삶의 여러 부분에서 이용할 수 있기 때문에 중요한 주제이다. 건강관리를 위한 조언을 제공하는데 사용될 수 있기 때문에 동작인식 중 일상생활 동작인식이 주로 연구되고 있다. 특별히 넘어짐은 심장문제로 발생할 수 있기 때문에 넘어짐 인식은 독거 노인의 건강한 삶에 중요한 역할을 할 수 있다. 넘어짐 인식은 여전히 어려운 연구과제이다. 넘어짐 인식을 위해 몸에 여러 종류의 센서를 부착하는 시스템이 제안되었지만 이는 사용자가 센서를 부착하는 것을 잊어버리거나 이런 시스템에 익숙하지 않기 때문에 유용성에 문제가 있다. 본 연구에서는 사용자가 휴대하고 있는 스마트 폰 내의 가속도 및 자이로센서 값의 변화를 분석하여 알려진 넘어짐 패턴과 유사성을 분석하여 넘어짐을 판단하는 방법을 제안한다. 이 연구를 위해 5명의 자원자를 모집하여 다양한 종류의 넘어짐을 실험하였다. 실험결과는 본 연구를 통해서 넘어짐 인식을 위한 제안한 방식이 유효하다는 것을 보여준다. 실험 알고리즘은 많이 사용되고 있는 G1 스마트 폰 위에 구현하였다.

動的計画法 (DP) [1], [2]に基づくパターンマッチン グ法—DPマッチング—は,音声パターンの非線形対 応付け(弾性マッチング)を目的として 1970 年代に 開発された [3]~[5].その後応用範囲は広がり,今では パターン認識・画像処理における基本的道具の一つと なっている [6]~[8].特に,音声やオンライン文字デー タ,ジェスチャなどの時系列パターンの弾性マッチング 問題に対しては,非常に多くの場合において DPマッ チングが利用されている.同問題に対してHMMが利 用されることもあるが,HMMのゆう度計算のビタビ アルゴリズムが DPマッチングと等価な処理であるこ とを考えると,ほとんどすべての場合について,DP マッチングが利用されているという見方もできよう. このDPマッチングの特徴は,長さ I と J の二つの 一次元パターンに対し,それらの大局的に最適な非線 形対応付けを O(IJ) の計算量で求める点にある.オ ンライン文字パターンを例にすると,パターン長は文 字パターンを表現するデータ点の数に相当し,たかだ

„How can proper controller adjustments be quickly determined on any control application?” The question posed by authors of the first published PID tuning method J.G.Ziegler and N.B.Nichols in 1942 is still topical and challenging for control engineering community. The reason is clear: just every fifth controller implemented is tuned properly but in fact:  30% of improper performance is due to inadequate selection of controller design method,  30% of improper performance is due to neglected nonlinearities in the control loop,  20% of improper closed-loop dynamics is due to poorly selected sampling period. Although there are 408 various sources of PID controller tuning methods (O Dwyer, 2006), 30% of controllers permanently operate in manual mode and 25% use factory-tuning without any up-date with respect to the given plant (Yu, 2006). Hence, there is natural need for effective PID controller design algorithms enabling not only to modify the controlled variable but also achieve specified performance (Kozakova et al., 2010), (Osuský et al., 2010). The chapter provides a survey of 51 existing practice-oriented methods of PID controller design for specified performance. Various options for design strategy and controller structure selection are presented along with PID controller design objectives and performance measures. Industrial controllers from ABB, AllenB these methods are based on minimum information about the plant obtained by the well-known relay experiment. Model-based PID controller tuning techniques acquire plant parameters from a step-test; useful tuning formulae are provided for commonly used system models (FOPDT – first-order plus dead time, IPDT – integrator plus dead time, FOLIPDT – first-order lag and integrator plus dead time and SOPDT – second-order plus dead time). Optimization-based PID tuning approaches, tuning methods for unstable plants, and design techniques based on a tuning parameter to continuously modify closed-loop performance are investigated. Finally, a novel advanced design technique based on closed-loop step response shaping is presented and discussed on illustrative examples.

”Extension du corps sonore” is long-term project initiated by Musiques Nouvelles [4], a contemporary music ensemble in Mons. It aims at giving instrumental music performers an extended control over the sound of their instrument by extending the understanding of the sound body from the instrument only to the combination of the instrument and the whole body of the performer. The development started at ARTeM and got the benefit of a three month numediart research project [1] that focused on three axes of research: pre-processing of sensor data, gesture recognition and mapping through interpolation. The objectives were the development of computing methods and flexible Max/MSP externals to be later integrated in the ARTeM software framework for the concerts with viola player Dominica Eyckmans. They could be used in a variety of other artistic works and will be made available on the numediart website [1], where more detailed information can be found in the Quarterly Progress Scientific Report #4.

“Jarvis” was main character of Tony’s Stark’s life assistant in Movies Iron Man. Unlike original comic in which Jarvis was Stark’s human butler, the movie version of Jarvis is an intelligent computer that converses with stark, monitors his household and help to build and program his superhero suit. In this Project Jarvis is Digital Life Assistant which uses mainly human communication means such Twitter, instant message and voice to create two way connections between human and his apartment, controlling lights and appliances, assist in cooking, notify him of breaking news, Facebook’s Notifications and many more. In our project we mainly use voice as communication means so the Jarvis is basically the Speech recognition application. The concept of speech technology really encompasses two technologies: Synthesizer and recognizer. A speech synthesizer takes as input and produces an audio stream as output. A speech recognizer on the other hand does opposite. It takes an audio stream as input and thus turns it into text transcription. The voice is a signal of infinite information. A direct analysis and synthesizing the complex voice signal is due to too much information contained in the signal. Therefore the digital signal processes such as Feature Extraction and Feature Matching are introduced to represent the voice signal. In this project we directly use speech engine which use Feature extraction technique as Mel scaled frequency cepstral. The melscaled frequency cepstral coefficients (MFCCs) derived from Fourier transform and filter bank analysis are perhaps the most widely used frontends in state-of-the-art speech recognition systems. Our aim to create more and more functionalities which can help human to assist in their daily life and also reduces their efforts. In our test we check all this functionality is working properly. We test this on 2 speakers(1 Female and 1 Male) for accuracy purpose.

“Embodied visual navigation” problem requires an agent to navigate in a 3D environment mainly rely on its first-person observation. This problem has attracted rising attention in recent years due to its wide application in vacuum cleaner, and rescue robot, etc. A navigation agent is supposed to have various intelligent skills, such as visual perceiving, mapping, planning, exploring and reasoning, etc. Building such an agent that observes, thinks, and acts is a key to real intelligence. The remarkable learning ability of deep learning methods empowered the agents to accomplish embodied visual navigation tasks. Despite this, embodied visual navigation is still in its infancy since a lot of advanced skills are required, including perceiving partially observed visual input, exploring unseen areas, memorizing and modeling seen scenarios, understanding cross-modal instructions, and adapting to a new environment, etc. Recently, embodied visual navigation has attracted rising attention of the community, and numerous works has been proposed to learn these skills. This paper attempts to establish an outline of the current works in the field of embodied visual navigation by providing a comprehensive literature survey. We summarize the benchmarks and metrics, review different methods, analysis the challenges, and highlight the state-of-the-art methods. Finally, we discuss unresolved challenges in the field of embodied visual navigation and give promising directions in pursuing future research.

—The paper addresses the problem of transferring new skills to robots from observation of human demonstrated skill examples. An approach is presented for retrieving trajectories of an object, being manipulated during the demonstrations, from Kinect-provided measurements. The problem of object tracking across the image frames is solved by using weighted dynamic template matching with normalized cross-correlation. Such approach takes advantage of the simultaneous image and depth measurements by the Kinect device in leveraging the pattern localization and pose estimation. Demonstrated trajectories are stochastically encoded with hidden Markov model, and the obtained model is exploited for generation of a generalized trajectory for task reproduction. The developed methodology is experimentally validated in a real-world task learning scenario.

© 2012 Cassisi et al., licensee InTech. This is an open access chapter distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Similarity Measures and Dimensionality Reduction Techniques for Time Series Data Mining

xiii Zusammenfassung xvii

vii

vii

tslearn is a general-purpose Python machine learning library for time series that offers tools for pre-processing and feature extraction as well as dedicated models for clustering, classification and regression. It follows scikit-learn's Application Programming Interface for transformers and estimators, allowing the use of standard pipelines and model selection tools on top of tslearn objects. It is distributed under the BSD-2-Clause license, and its source code is available at https://github.com/tslearn-team/tslearn.

this paper, we propose novel techniques for feature parameter extraction based on MFCC and feature recognition using dynamic time warping algorithm for application in speaker-independent isolated digits recognition. Using the proposed Weighted MFCC (WMFCC), we achieve low computational overhead for the feature recognition stage since we use only 13 weighted MFCC coefficients instead of the conventional 39 MFCC coefficients including the delta and double delta features. In order to capture the trends or patterns that a feature sequence presents during the alignment process, we compute the local and global features using Improved Features for DTW algorithm (IFDTW), rather than using the pure feature values or their estimated derivatives. The experiments based on TI-Digits corpus demonstrate the effectiveness of proposed techniques leading to higher recognition accuracy of 98.13%.

this paper, a method is proposed for feature extraction of offline signature recognition system. The proposed method is based on global features to identify forgeries and also median filter is introduces for noise reduction. The Proposed feature extraction method is compared with Discrete Radon Transform (DRT). Both the feature extraction method extracts one dimensional global features and the alignment between features is performed by Dynamic Time Warping (DTW). When being trained using 6 genuine signatures of each person and 250 forgeries taken from our database, the proposed method obtained an equal error rate (EER) of 8.40%. The false acceptance rate (FAR) for proposed method was also kept as low as 8.80%. Keywordsfilter, Global features, Discrete Radon transform, Dynamic time warping.

textabstractMotion artefacts from involuntary changes in eye fixation remain a major imaging issue in optical coherence tomography (OCT). This paper reviews the state-of-the-art of retrospective procedures to correct retinal motion and axial eye motion artefacts in OCT imaging. Following an overview of motion induced artefacts and correction strategies, a chronological survey of retrospective approaches since the introduction of OCT until the current days is presented. Pre-processing, registration, and validation techniques are described. The review finishes by discussing the limitations of the current techniques and the challenges to be tackled in future developments.

s of Invited Talks Causal Inference and Machine Learning: Estimating and Evaluating Policies

pyts is an open-source Python package for time series classification. This versatile toolbox provides implementations of many algorithms published in the literature, preprocessing functionalities, and data set loading utilities. pyts relies on the standard scientific Python packages numpy, scipy, scikit-learn, joblib, and numba, and is distributed under the BSD-3-Clause license. Documentation contains installation instructions, a detailed user guide, a full API description, and concrete self-contained examples. Source code and documentation can be downloaded from https://github.com/johannfaouzi/pyts.

presence of a professional may cause adverse event or lead to secondary injury. In this paper, we describe our development of a Kinect-based system - KHRD using Dynamic Time Warping (DTW) algorithm and fuzzy logic for ensuring home-based rehabilitation. The KHRD allows a patient perform a prescribed exercise with the presence of a professional. The exercise performed will then be recorded as a base for evaluating the patient's rehabilitation exercise at home. The outcomes of the evaluation can be used as a reference for the patient to validate his/her exercise and to prevent adverse events. A summary report of the outcomes may also be uploaded to a cloud setting for physicians to monitor the patient's progress and adjust the prescription. B. Kinect