Efficient Training Algorithms for HMMs Using Incremental Estimation (2007)
Yoshihiko Gotoh, Michael M. Hochberg, Harvey F. Silverman
Typically, parameter estimation for a hidden Markov model (HMM) is performed using an expectation-maximization (EM) algorithm with the maximum-likelihood (ML) criterion. The EM algorithm is an...
Silverman, Harvey F., Kirtman, Stuart E., Adock, John E., Meuse, Paul C.
In this paper, baseline speech recognition performance is determined both for a single remote microphone and for a signal derived from a delay-and-sum beamformer using an eight-microphone linear...
III. Large vs small aperture microphone arrays: Performance over a large focal area (2001)
Joshua M. Sachar, Harvey F. Silverman
Microphone arrays offer the potential of obtaining a high-quality speech signal from a remote talker in a noisy, multi-source environment. In many important applications, sources of interest may be...
An Experiment That Validates Theory With Measurments For A (2001)
Harvey F. Silverman, Joshua M. Sachar
Poor sound pick up by remote microphones in multimedia applications, conference rooms and auditoria has traditionally hampered speech recognition and communication among spatially-separated groups....
Multicovariance Matched Filter for Target Detection in Images. (1998)
Scheffe, Molly M., Cooper, David B., Silverman, Harvey F., Blane, Michael M.
Our original research on the multicovariance matched filter deals with optimum low resolution target detection in a single-frame, multicolor image, such as a multispectral infrared or polarimetric...
A Closed-Form Location Estimator for Use with Room Environment Microphone Arrays (1997)
Michael S. Brandstein, Michael S. Br, John E. Adcock, Harvey F. Silverman
Introduction Microphone-array systems can be used to determine the positions of active talkers and can be electronically steered to provide spatially-selective speech acquisition. Since it is steered...
A Robust Method For Speech Signal Time-Delay Estimation In Reverberant Rooms (1997)
Michael S. Brandstein, Harvey F. Silverman
Conventional time-delay estimators exhibit dramatic performance degradations in the presence of multipath signals. This limits their application in reverberant enclosures, particularly when the...
A Closed-Form Location Estimator for Use with Room Environment Microphone Arrays (1997)
Michael Brandstein, Michael S. Br, John E. Adcock, Harvey F. Silverman
Introduction Microphone-array systems can be used to determine the positions of active talkers and can be electronically steered to provide spatially-selective speech acquisition. Since it is steered...
The Huge Microphone Array (HMA) (1996)
Harvey F. Silverman, James L. Flanagan
The Huge Microphone Array(HMA) is a project that started in February 1994 to design, construct, debug, and test a real-time 512-microphone array system and to develop algorithms for use on it....
Microphone-Array Speech Recognition Via Incremental Map Training (1996)
John Adcock, Yoshihiko Gotoh, Daniel J. Mashao, Harvey F. Silverman
For a hidden Markov model (HMM) based speech recognition system it is desirable to combine enhancement of the acoustical signal and statistical representation of model parameters, ensuring both a...
Tracking Multiple Talkers Using Microphone-Array Measurements (1996)
Douglas Sturim, Michael S. Brandstein, Harvey F. Silverman, Laboratory Engineering
A method for tracking the positional estimates of multiple talkers in the operating region of an acoustic microphone array is presented. Initial talker location estimates are provided by a...
Incremental Ml Estimation Of Hmm Parameters For Efficient Training (1996)
Yoshihiko Gotoh, Harvey F. Silverman
Conventional training of a hidden Markov model (HMM) is performed by an expectation-maximization algorithm using a maximum likelihood (ML) criterion. Recently it was reported that, using an...
A Localization-Error-Based Method For Microphone-Array Design (1996)
Michael S. Brandstein, John E. Adcock, Harvey F. Silverman, Laboratory Engineering
This paper presents a means for predicting the error region associated with a speech-source location estimate obtained from a set of microphones in a room environment. The error predictor presented...
A Practical Time-Delay Estimator for Localizing Speech Sources with a Microphone Array (1995)
Michael S. Brandstein, Michael S. Br, John E. Adcock, Harvey F. Silverman
A frequency-domain-based delay estimator is described, designed specifically for speech signals in a microphone-array environment. It is shown to be capable of obtaining precision delay estimates...
Microphone-Array Localization Error Estimation with Application to Sensor Placement (1995)
Michael Brandstein, Michael S. Br, John E. Adcock, Harvey F. Silverman
This paper presents a means for predicting the error region associated with a speech-source location estimate obtained from a set of microphones in a room environment. The error predictor presented...
A Practical Time-Delay Estimator for Localizing Speech Sources with a Microphone Array (1995)
Michael Brandstein, Michael S. Br, John E. Adcock, Harvey F. Silverman
A frequency-domain-based delay estimator is described, designed specifically for speech signals in a microphone-array environment. It is shown to be capable of obtaining precision delay estimates...
Analysis of LPC/DFT Features for an HMM-based Alphadigit Recognizer (1995)
Daniel Mashao, Yoshihiko Gotoh, Harvey F. Silverman
The search for better and more robust performance of speech recognition systems is ongoing. Much of the improvement is likely to come from better acoustic feature analysis. In this letter, the...
Characterization of talker radiation pattern using a microphone array (1994)
Paul C. Meuse, Harvey F. Silverman
A microphone array has the capability of capturing the properties of a significant portion of a talker's radiation pattern. In this paper, potential implications of measuring the radiation...
John Adcock, Joseph H. Dibiase, Michael S. Br, Harvey F. Silverman
A frequency-domain delay estimator has been used as the basis of a microphone-array talker location and beamforming system [Brandstein, M.S., and Silverman, H.F., Technical Report LEMS116, (1993)] ....
Using Map Estimated Parameters To Improve HMM Speech Recognition Performance (1994)
Yoshihiko Gotoh, Michael M. Hochberg, Harvey F. Silverman
Hidden Markov models (HMMs) have been quite successfully applied to speech recognition tasks, but many unsolved problems still remain. HMMs do not directly model all phenomena that might be useful...
The Hardware and Communication Architecture of the Armstrong III Multiprocessor (1994)
Aaron T. Smith, Aaron T. Smith, Aaron T. Smith, Harvey F. Silverman
for the many hours of teamwork necessary to build such a project as Armstrong III. Lalit Agarwal for theoretical discussion of much meaning. The Laboratory for Engineering Man/Machine Systems would...
Processor reconfiguration through instruction-set metamorphosis (1993)
Peter M. Athanas, Harvey F. Silverman
Many computationally-intensive tasks spend nearly all of their execution time within a small fraction of the executable code. A new hardware/software system, called PRISM, is presented which improves...
Harvey F. Silverman, Smart E. Kirtman, John E. Adcock, Paul C. Meuse
In this paper, baseline speech recognition performance is determined both for a single remote microphone and for a signal derived from a delay-and-sum beamformer using an eight-microphone linear...
Incremental Map Estimation Of HMMs For Efficient Training And Improved Performance
Yoshihoko Gotoh, Michael M. Hochberg, Daniel J. Mashao, Harvey F. Silverman
Continuous density observation hidden Markov models (CD-HMMs) have been shown to perform better than their discrete counterparts. However, because the observation distribution is usually represented...
A Closed-Form Method For Finding Source Locations From Microphone-Array Time-Delay Estimates
Michael S. Brandstein, Michael S. Br, John E. Adcock, Harvey F. Silverman
The linear intersection (LI) estimator, a closed-form method for the localization of source positions given only the sensor array time-delay estimate information, is presented. The array is...