Publications

This paper studies the structure of foreign-accented read English speech. A system for accent identification is constructed by combining linguistic theory with statistical analysis. Results demonstrate that the linguistic theory is reflected in real speech data and its application improves accent identification. The work discussed here combines and applies previous...

Performance variability in speech and speaker recognition systems can be attributed to many factors. One major factor, which is often acknowledged but seldom analyzed, is inherent differences in the recognizability of different speakers. In speaker recognition systems such differences are characterized by the use of animal names for different types...

We examine vulnerabilities of several reliable multicast protocols. The various mechanisms employed by these protocols to provide reliability can present vulnerabilities. We show how some of these vulnerabilities can be exploited in denial-of-service attacks, and discuss potential mechanisms for withstanding such attacks.

We describe an approach to estimating the amplitude-modulated (AM) and frequency-modulated (FM) components of a signal. Any signal can be written as the product of an AM component and an FM component. There have been several approaches to solving the AM-FM estimation problem described in the literature. Popular methods include...

A method is described for estimating telephone handset nonlinearity by matching the spectral magnitude of the distorted signal to the output of a nonlinear channel model, driven by an undistorted reference. The "magnitude-only" representation allows the model to directly match unwanted speech formants that arise over nonlinear channels and that...

Based on a sinusoidal model, an analysis/synthesis technique is developed that characterizes audio signals, such as speech and music, in terms of the amplitudes, frequencies, and phases of the component sine waves. These parameters are estimated by applying a peak-picking algorithm to the short-time Fourier transform of the input waveform...

A high-performance low-complexity neural network wordspotter was developed using radial basis function (RBF) neural networks in a hidden Markov model (HMM) framework. Two new complementary approaches substantially improve performance on the talker independent Switchboard corpus. Figure of Merit (FOM) training adapts wordspotter parameters to directly improve the FOM performance metric...

A noise reduction algorithm is designed for the aural enhancement of short-duration wideband signals. The signal of interest contains components possibly only a few milliseconds in duration and corrupted by nonstationary noise background. The essence of the enhancement technique is a Weiner filter that uses a desired signal spectrum whose...

This paper compares two approaches to background model representation for a text-independent speaker verification task using Gaussian mixture models. We compare speaker-dependent background speaker sets to the use of a universal, speaker-independent background model (UBM). For the UBM, we describe how Bayesian adaptation can be used to derive claimant speaker...

Language-identification (LID) techniques that use multiple single-language phoneme recognizers followed by n-gram language models have consistently yielded top performance at NIST evaluations. In our study of such systems, we have recently cut our LID error rate by modeling the output of n-gram language models more carefully. Additionally, we are now...