Improving on hidden Markov models: An articulatorily constrained, maximum likelihood approach to speech recognition and speech coding (open access)

Improving on hidden Markov models: An articulatorily constrained, maximum likelihood approach to speech recognition and speech coding

The goal of the proposed research is to test a statistical model of speech recognition that incorporates the knowledge that speech is produced by relatively slow motions of the tongue, lips, and other speech articulators. This model is called Maximum Likelihood Continuity Mapping (Malcom). Many speech researchers believe that by using constraints imposed by articulator motions, we can improve or replace the current hidden Markov model based speech recognition algorithms. Unfortunately, previous efforts to incorporate information about articulation into speech recognition algorithms have suffered because (1) slight inaccuracies in our knowledge or the formulation of our knowledge about articulation may decrease recognition performance, (2) small changes in the assumptions underlying models of speech production can lead to large changes in the speech derived from the models, and (3) collecting measurements of human articulator positions in sufficient quantity for training a speech recognition algorithm is still impractical. The most interesting (and in fact, unique) quality of Malcom is that, even though Malcom makes use of a mapping between acoustics and articulation, Malcom can be trained to recognize speech using only acoustic data. By learning the mapping between acoustics and articulation using only acoustic data, Malcom avoids the difficulties involved in collecting …
Date: November 5, 1996
Creator: Hogden, J.
System: The UNT Digital Library
Minimum TI4085D interlock setpoint at 1.0 GPM sludge-only feed rate and 14,000 ppm TOC (open access)

Minimum TI4085D interlock setpoint at 1.0 GPM sludge-only feed rate and 14,000 ppm TOC

DWPF-Engineering requested that SRTC determine the minimum indicated melter vapor space temperature that must be maintained in order to minimize the potential for off-gas flammability during a steady sludge-only feeding operation at 1.0 GPM containing 14,000 ppm total organic carbon. The detailed scope of this request is described in the technical task request, HLW-DWPF-TTR-960092 (DWPT Activity No. DWPT-96-0065). In response to this request, a dynamic simulation study was conducted in which the concentration of flammable gases was tracked throughout the course of a simulated 3X off-gas surge using the melter off-gas (MOG) dynamics model. The results of simulation showed that as long as the melter vapor space temperature as indicated on TI4085D is kept at 570 degrees C or higher, the peak concentration of combustible gases in the melter off-gas system is not likely to exceed 60 percent of the lower flammability limit (LFL). The minimum TI4085D of 570 degrees C is valid only when the air purges to FIC3221A and FIC3221B are maintained at or above 850 and 250 lb/hr, respectively. All the key bases and assumptions along with the input data used in the simulation are described in the attached E-7 calculation note.
Date: November 5, 1996
Creator: Choi, A.S.
System: The UNT Digital Library