IIT Madras is a public technical and research university located in Chennai, Tamil Nadu. Founded in 1959, it is recognised as an Institute of National Importance.

IIT Madras has been ranked as the top engineering institute in India for four years in a row by the National Institutional Ranking Framework of the MHRD

It currently offers undergraduate, postgraduate and research degrees across 16 disciplines in Engineering, Sciences, Humanities and Management. About 596 faculty belonging to science and engineering departments and centres of the Institute are engaged in teaching, research and industrial consultancy.

IIT Madras

Our investigation into the front-end signal processing for maximum likelihood based speaker normalization reveals that in the linear scaling model, it is more appropriate (and evidently more correct) to assume that the spectral envelopes of any two speakers for same sound are linearly scaled versions of one and another, rather than assuming that the whole magnitude spectra (including pitch harmonics) are scaled. The use of the proposed model and its implementation results in about 4% and 7% relative improvement for adults and children respectively on a digit recognition task.

Department of Electrical Engineering

Department of Aerospace Engineering

Department of Metallurgical and Materials Engineering

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

An investigation into front-end signal processing for speaker normalization

Use of a continuation technique to automate the computation oF gain schedules for a flight control application is demonstrated. An interesting feature of this approach is that the computation of gain schedules and that of the equilibrium points over which the gains are to be scheduled are carried out simultaneously. The technique is illustrated with a stability augmentation system for an aircraft using data for the F-18/HARV open-loop dynamics available in the literature. Copyright © 1004 IFAC.

World University root node

IFAC Proceedings Volumes (IFAC-PapersOnline)

Automated gain scheduling using continuation techniques

In this paper, we propose a mathematical model to describe the relation between the formant frequencies of speakers and show that with the proposed affine model, speaker differences separate out as translation factors when a "mel-like" warping is performed. Using speech data we estimate the parameters of this warping function and show that it is close to the usual mel-formula. This model is motivated by Rohit et al.'s shift-based non-uniform speaker-normalization method, which provides improvement over the conventional maximum-likelihood based speaker normalization methods. We therefore provide a unified framework that relates the relationship between formants of speakers and method of removing speakers difference (which involves mel-warping) in a neat mathematical framework which is substantiated by our recognition experiments.

Non-uniform speaker normalization using affine-transformation

The extended bifurcation analysis (EBA) technique has been recently proposed for the bifurcation analysis of dynamical systems with constrained equilibrium states. In this paper, the EBA technique is used to investigate non-linear behaviour of an aircraft in constrained roll manoeuvres. A comparative performance analysis of the aircraft in three roll manoeuvres, viz. zero sideslip roll, velocity vector roll, and roll manoeuvre with a linear aileron-rudder interconnect (ARI), has been carried out. Selective numerical simulations are carried out to supplement the information obtained from bifurcation analysis.

Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering

Bifurcation analysis of inertia coupled roll manoeuvres of airplanes

AFM-3: Atmospheric Flight Mechanics Student Paper Competition

Automated Gain Scheduling for Level Flight Stability Augmentation Using Continuation Techniques

In the conventional maximum likelihood based speaker normalization approach, the optimal frequency warping factors are estimated by maximizing the likelihood of warped features in a grid search. The conventional method of likelihood computation for warped features does not account for the Jacobian of the transformation. This fact is pointed out by some researchers who have also shown that frequency warping is equivalent to the transformation in cepstral domain. As an approximation, variance normalization of cepstral features is used before likelihood computation to account for the Jacobian. In this paper, we suggest an alternate method to avoid the Jacobian problem. Our preliminary investigation shows that our proposed method provides improvement in normalization performance compared to the conventional method of warping factor estimation for a digit recognition task.

A method for compensation of Jacobian in speaker normalization

The Extended Bifurcation Analysis (EBA) technique is a continuation procedure which can be applied to efficiently generate bifurcation diagrams for parameterized nonlinear dynamical systems with constraints. Desired constraints can be appended to the system equations and appropriate control parameters can be scheduled as functions of the operating control parameter so that the constraints are always satisfied. This technique has been used recently to generate bifurcation diagrams and performance plots for an aircraft in straight and level, and zero sideslip level turning flights. Flexibility of this technique allows any number of constraints to be exercised on the system provided there are as many control parameters available that influence the constraints. In this manner, control objectives can be described as constraint functions, and control laws that control bifurcation behavior of nonlinear dynamical systems can be designed by using the EBA method. In this paper, application of the EBA technique to flight control law design based on avoiding bifurcations has been illustrated with two example problems. © 2002 by the American Institute of Aeronautics and Astronautics, Inc.

40th AIAA Aerospace Sciences Meeting and Exhibit

Use of the Extended Bifurcation Analysis method for flight control law design

Journal of Aircraft

Maximum steady roll rate in zero-sideslip roll maneuvers of aircraft

We present experimental results that show better speaker normalization using our previously reported frequency warping function that is derived purely from speech data. In our previous work, we have numerically computed the frequency warping function for non-uniform scaling, which is similar to mel-scale, such that spectral envelopes from different speakers enunciating the same sound are similar except for a possible translation factor. In this paper, we do a maximum likelihood search for these translation parameters and show that this non-uniform normalization scheme provides about 18% improvement over the normalization method based on the maximum likelihood estimate of uniform scaling parameters and about 30% improvement over mel filterbank cepstral coefficient based baseline for a telephone based continuous digit recognition task. The other attractive attribute of the proposed method is the simplicity in generating features with different shifts compared to generating features with different warping factors in earlier methods.

Non-uniform scaling based speaker normalization

In this paper, we present results of non-uniform vowel normalization and show that the frequency-warping necessary to do nonuniform vowel normalization is similar to the mel-scale. We compare our methods to Fant’s non-uniform vowel normalization method and show that with proposed frequency warping approach we can achieve similar performance without any knowledge of the spoken vowel and the formant number. The proposed approach is motivated by a desire to perform non-uniform speaker normalization in automatic speech recognition systems. We also present results of a more comprehensive study of our earlier work on non-uniform scaling which again shows that mel-scale is the appropriate warping function. All the results in this paper are based on data from Peterson & Barney and Hillenbrand et al. vowel databases.

Department of Ocean Engineering

A simple approach to non-uniform vowel normalization

Level Flight Trim and Stability Analysis Using Extended Bifurcation and Continuation Procedure

Bifurcation and continuation methods have been widely used over the last two decades for the prediction of aircraft flight instabilities. These methods have also found application in control law design, and in devising recovery strategies from difficult flight conditions like spin. Very recently, continuation methods have emerged as an efficient technique for generating trim points in constrained flight for use in controller design, and for aircraft performance evaluation. Previous studies using bifurcation methods in the presence of constraints could not recover information about the stability of the trim points, and did not seek to trace departures from the constrained flight at points of instability. In this paper, we describe an extended bifurcation and continuation procedure that overcomes these drawbacks. The procedure is illustrated by computing trim points for two different level flight conditions: straight flight, and zero sideslip turns. Standard straight and level flight, and level turn performance plots are produced by this procedure with little effort. These plots also carry stability information of each trim point, and show all possible motions that depart from the constrained flight. The procedure can be applied to other constrained trim flights with equal ease. © 2000 by the American Institute of Aeronautics and Astronautics, Inc. AH rights reserved.