Publications

The performance of a speech recognizer is often degraded by noise.

We report on important limitations of the commonly used method to generate complex optical signal constellations from delay-decorrelated copies of a common bit sequence to modulate in-phase (I) and

* The work presented here is based, in part, on the MS thesis, "A Comparative Study of Several Dynamic Time Warping Algorithms for Speech Recognition," by C. S. Myers, MIT, April 1980.

In the last few years it has become common to use LPC coding techniques for speech r e c o g n i t i o n .

In this paper we extend our investigations of the HMM recognizer to the recognition of isolated words from a medium size vocabulary (129 words), as used in the Bell Laboratories airlines reservatio

The Locality Sensitive Hashing (LSH) technique of scalably finding nearest-neighbors can be adapted to enable discovering similar users while preserving their privacy.

In this work, an integrated approach to vector dynamic feature extraction is described in the design of a hidden Markov model (VVD-IHMM) based speech recognizer.

Although variable capacitance amplifiers have been built and operated successfully, their design has been an art practiced by the individual designer rather than a systematic construction.

Predicting the life cycle and the short-term popularity of a Web object is important for network architecture optimization.

There has been recent interest in the use of the crossover as a multistage interconnection network in optical systems.