Learn More
An important aspect of distinctive feature based approaches to automatic speech recognition is the formulation of a framework for robust detection of these features. We discuss the application of the support vector machines (SVM) that arise when the structural risk minimization principle is applied to such feature detection problems. In particular, we(More)
We consider the possibility of incorporating distinctive features into a statistically based speech recognizer. We develop a two pass strategy for recognition with a standard HMM based first pass followed by a second pass that performs an alternative analysis to extract class-specific features. For the voiced/voiceless distinction on stops for an alphabet(More)
Utterance verification is used in spoken language dialog systems to reject the speech that does not belong to the task and to correctly recognize the sentences that do. Current verification systems use context dependent (CD) or context independent (CI) subword models and CI anti-subword models. We propose many methods of modeling the CD anti-subword models.(More)
We examine the distinctive feature [voice] that separates the voiced from the unvoiced sounds for the case of stop consonants. We conduct acoustic-phonetic analyses on a large database and demonstrate the superior separability using a temporal measure (voice onset time; VOT) rather than spectral measures. We describe several algorithms to estimate the VOT(More)
 Abstract— Wavelet Transform is a time-frequency representation of the input signal. Realization of wavelet transform on field-programmable gate array (FPGA) device for the detection of power system disturbances is proposed in this thesis. This approach provides an integral signal-processing paradigm, where its embedded wavelet basis serves as a window(More)
This paper addresses the new algebraic test to check the aperiodic stability of two dimensional linear time invariant discrete systems. Initially, the two dimensional characteristics equations are converted into equivalent one-dimensional equation. Further Fuller's idea is applied on the equivalent one-dimensional characteristics equation. Then using the(More)
The Euler-Bernoulli's method is used to model the dynamics of single link flexible manipulator. Model is highly nonlinear in nature, consists of partial differential equations, and so with the help of MATLAB & SIMULINK is taken. The state space model is designed by using S function block in SIMULINK and it's M-file in MATLAB. The response of the model is(More)