Publications

The global and fine dynamic components of a pitch contour in voice production, as in the speaking and singing voice, are important for both the meaning and character of an utterance. In speech, for example, slow pitch inflections, rapid pitch accents, and irregular regions all comprise the pitch contour. In...

This paper presents a minimum classification error (MCE) training approach for improving the accuracy of multi-class support vector machine (SVM) classifiers. We have applied this approach to topic identification (topic ID) for human-human telephone conversations from the Fisher corpus using ASR lattice output. The new approach yields improved performance over...

Preliminary results are reported from a very simple speech-synthesis system based on clustered-diphone Kalman Filter based modeling of line-spectral frequency based features. Parameters were estimated using maximum-likelihood EM training, with a constraint enforced that prevented eigenvalue magnitudes in the transition matrix from exceeding 1. Frames of training data were assigned...

This paper presents a description of the MIT Lincoln Laboratory language recognition system submitted to the NIST 2009 Language Recognition Evaluation (LRE). This system consists of a fusion of three core recognizers, two based on spectral similarity and one based on tokenization. The 2009 LRE differed from previous ones in...

Graphs are canonical examples of high-dimensional non-Euclidean data sets, and are emerging as a common data structure in many fields. While there are many algorithms to analyze such data, a signal processing theory for evaluating these techniques akin to detection and estimation in the classical Euclidean setting remains to be...

We propose supervised and unsupervised learning algorithms to extract dialect discriminating phonetic rules and use these rules to adapt biphones to identify dialects. Despite many challenges (e.g., sub-dialect issues and no word transcriptions), we discovered dialect discriminating biphones compatible with the linguistic literature, while outperforming a baseline monophone system by...

The long-term objectives for the NextGen Weather Processor (NWP) include consolidation of today's multiple weather systems, incorporation of recent and emerging Federal Aviation Administration (FAA) infrastructure (Federal Telecommunications Infrastructure (FTI), System Wide Information Management (SWIM), NextGen Network-Enabled Weather (NNEW)), leveraging National Oceanic and Atmospheric Administraiton (NOAA) and/or commercial weather resources...

Airspace encounter models, providing a statistical representation of geometries and aircraft behavior during a close encounter, are required to estimate the safety and robustness of collision avoidance systems. Prior encounter models, developed to certify the Traffic Alert and Collision Avoidance System, have been limited in their ability to capture important...

Ultralow-power electronics will expand the technological capability of handheld and wireless devices by dramatically improving battery life and portability. In addition to innovative low-power design techniques, a complementary process technology is required to enable the highest performance devices possible while maintaining extremely low power consumption. Transistors optimized for subthreshold operation...

The Traffic Alert and Collision Avoidance System (TCAS) is designed to reduce the risk of mid-air collisions by providing resolution advisories to pilots. The current version of the collision avoidance logic was hand-crafted over the course of many years and contains many parameters that have been tuned to varying extents...