[ ] P. Lanchantin, N. Obin and X. Rodet, Extended Conditional GMM and Covariance Matrix Correction for Real-Time Spectral Voice Conversion, submitted to Interspeech 2011, Florence, Italy, 2011
Historical background, Types, Manufacturing Methods, Functions, Typical Applications; Geosynthetic Testing, Physical, Mechanical, Construction survivability and durability testing of Geotextiles and Geogrids; Principles of Soil Reinforcement, Types of Reinforcement, Testing, Allowable loads for design (creep etc.), Elements of Design + NCMA Method, Fill Material, Detailed Design of Reinforced Soil Walls (BS 8006), Reinforced Slopes (BS 8006), Facia and Construction Methodology, Specifications, Bearing capacity Improvement, Embankments on soft soils, Basal Reinforcement – Design, Geocell – Design, Construction and Specification, IRC/MORTH Guidelines, Case Histories; Filteration and Drainage, Principles, Typical applications, Dams, French Drains, Testing, Design Principles, Specifications; Pavements and Airports; Influence of cyclic loading, Design for soft soils (unpaved) and new construction – Granular layers, GS in Bituminous Pavements – new construction and rehabilitation, Construction and specifications, Rural Road applications, Railway Tracks, Indian experiences; Natural fibre Materials, Jute and Coir Geotextiles - Products, Processes; Environmental Control, Erosion Control, Mechanics of Erosion, Methods of Control, Products, Design for various conditions, Silt Control, Land slides – Occurrence and methods of mitigation, Liners for Pounds and Canals; Engineered Landfills, Municipal Solid Waste, Hazardous Waste Landfills, Site location –MOEF Guidelines, Covers and liners, GCLs, Material aspects and, Design, construction and maintenance, the Indian Scenario
My research area is Statistical Signal Processing. My main topics of research include statistical modeling of signals, speech processing and their applications to Music. My research has focused initially on the generalization of statistical models for signals, especially Hidden Markov Models (HMM). I studied during my [ ] models called Triplet Markov models that generalize the classical HMM (Hidden Markov Models (HMM)), with applications in image segmentation. I then directed my research toward speech processing, working on the segmentation of speech signals into phones, voice conversion, language models and HMM-based speech synthesis. My research studies on speech are interdisciplinary as they combine statistical modeling of signals, natural language processing and their application to music.
The principle of Voice conversion is to transform the signal from the voice of a source speaker, so it seems to have been issued by a target speaker. Conversion techniques studied at IRCAM by F. Villavicencio and then by myself under the ANR Affective Avatars are based on Gaussian Mixture Models (GMM). Typically, the joint distribution of acoustic source and target characteristics, modeled by a GMM, is estimated from a parallel corpus consisting of synchronous recordings of source and target speakers. The conversion function is then given by the conditional expectation to the acoustic characteristics of the source. My studies have focused both on the definition of the transformation function on its application to improve the quality of converted speech. Thus, all-pole modeling of the spectral envelope has been improved by the True-Envelope technics that enhances the quality of the synthesis and the characterization of the residual from the speaker. On the other hand, the use of the covariance matrix of the conditional distribution to the acoustic characteristics of the source allows a renormalization of the transformed characteristics in order to improve the quality of the converted signal. Finally, during the project, I proposed a method for Dynamic Model Selection (DMS [ , ) which consits in using several models of different complexity and to select the most appropriate model for each frame of analysis during the conversion. The results of voice conversion obtained are very encouraging. Thus, it appears that the "personality" of the target speaker is well reproduced after processing and that the source speaker has largely disappeared. The main difficulty that remains is some degradation of sound quality of voice. However, other ways of improvements we are currently investigating [ ] are expected to arrive at a usable quality, real-time, even for very demanding applications, such as artistic applications.
Introduction to human visual perception – visual system, eye, constancy, continuation, shadows; Graphics pipeline; Mathematical foundations – sets, functions, coordinates, operations on coordinates, intersections, triangles, polygons; Introduction to OpenGL and WebGL; Shaders – vertex, fragment, GLSL; Transformations – 2D, 3D; Cameras and transformations – perspective and orthographic; Ray casting and rasterization; Basic image processing tools and techniques – convolution, sampling, aliasing, Fourier transform, enlarging, shrinking; Textures – mapping, synthesis; Interaction techniques – multi-touch, mouse-based; Splines – polynomial curves, Hermite curve, cubic B-splines; Meshes – topology, geometry, applications; Light – physics, measurement, reflectance; Materials and scattering – object-level, surface, models; Color – perception, color spaces; Principles of ray tracing and rendering; Basics of motion and animation; Graphics hardware basics.