Advances in speech transcription at IBM under the DARPA EARS program

This paper describes the technical and system building advances made in IBM's speech recognition technology over the course of the Defense Advanced Research Projects Agency (DARPA) Effective Affordable Reusable Speech-to-Text (EARS) program. At a technical level, these advances include the development of a new form of feature-based minimum phone error training (fMPE), the use of large-scale discriminatively trained full-covariance Gaussian models, the use of septaphone acoustic context in static decoding graphs, and improvements in basic decoding algorithms. At a system building level, the advances include a system architecture based on cross-adaptation and the incorporation of 2100 h of training data in every system component. We present results on English conversational telephony test data from the 2003 and 2004 NIST evaluations. The combination of technical advances and an order of magnitude more training data in 2004 reduced the error rate on the 2003 test set by approximately 21% relative-from 20.4% to 16.1%-over the most accurate system in the 2003 evaluation and produced the most accurate results on the 2004 test sets in every speed category.     

Surface geometry of slide bearings after percussive burnishing

A review of literature about the effect of oil pockets on improvement of sliding elements tribological performance as well as about the changes of surface topography during “zero-wear” process is shown. The paper presents also the results of experimental investigations done in the Department of Manufacturing Processes and Production Organisation of Rzeszow University of Technology, connected with the creation of oil pockets on sliding surfaces. In order to simulate a deterministic surface a program for the visualisation of pits was written. The procedures for assessment of the oil pocket size of specific shape and oil pockets coverage are presented. The tendencies of changes of surface topography and oil pockets dimensions during “zero-wear” process are also described.     

The System HfO2-Y2O3-Er2O3

A mathematical model of the liquidus surface based on a reduced polynomial method was proposed for the system HfO₂-Y₂O₃-Er₂O₃. The results of calculations according to this model agree fairly well with the experimental data. Phase equilibria in the system HfO₂-Y₂O₃-Er₂O₃ were studied on melted (as-cast) and annealed samples using X-ray diffraction (at room and high temperatures) and micro-structural and petrographic analyses. The crystallization paths in the system HfO₂-Y₂O₃-Er₂O₃ were established. The system HfO₂-Y₂O₃-Er₂O₃ is characterized by the formation of extended solid solutions based on the fluorite-type (F) form of HfO₂ and cubic (C) and hexagonal (H) forms of Y₂O₃ and Er₂O₃. The boundary curves of these solid solutions have the minima at 2370°C (15. 5 mol% HfO₂, 49. 5 mol% Y₂O₃) and 2360°C (10. 5 mol% HfO₂, 45. 5 mol% Y₂O₃). No compounds were found to exist in the system investigated.     

Silicon‐containing heterocyclic polymers and thin films made therefrom

Thin films, in the range of tens of micrometers thickness, have been prepared by casting onto glass plates the chloroform or N‐methylpyrrolidone solutions of polyimides or poly(imide‐amide)s containing silicon and phenylquinoxaline units in the main chain. The polymers have been synthesized by solution polycondensation reaction of aromatic diamines having preformed phenylquinoxaline rings with bis(3,4‐dicarboxyphenyl)dimethylsilane dianhydride or with a diacid chloride resulting from the reaction of this dianhydride with p‐aminobenzoic acid. The polymers were easily soluble in polar aprotic solvents and showed high thermal stability. The free‐standing films exhibited good mechanical properties with tensile strengths in the range of 48–86 MPa, tensile modulus in the range of 1.25–2.22 GPa and elongation at break in the range of 3–37%. Electrical insulating properties of some polymer films were evaluated on the basis of dielectric constant and dielectric loss and their variation with frequency and temperature. The values of the dielectric constant at 10 kHz were in the range of 2.94–3.08 for polyimides and 3.89–4.49 for poly(imide‐amide)s. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 102: 3062–3068, 2006     

<Emphasis Type="Italic">In situ</Emphasis> monitoring of solid fat content by means of pulsed nuclear magnetic resonance spectrometry and ultrasonics

An ultrasonic technique was developed to study the crystallization process of edible fats on-line. A chirp wave was used instead of the conventional pulser signal, thus achieving a higher signal-to-noise ratio. This enabled measurements to be made in concentrated systems [≈20% solid fat content (SFC)] through a 8.11-cm thick sample without significant signal loss. Fat samples were crystallized at 20, 25, and 30°C at a constant agitation rate of 400 rpm for 90 min. The crystallization process was followed by ultrasonic spectroscopy and a low-resolution pulsed nuclear magnetic resonance spectrometer. Specific relationships were found between ultrasonic parameters [integrated response, time of flight (TF), and full width half maximum] and SFC. TF, which is an indirect measurement of the ultrasonic velocity (v), was highly correlated to SFC (r ²>0.9) in a linear fashion (v=2.601 SFC+1433.0).     

Shear Strength of Pre-Cast Prestressed Composite Beams with Discontinuous Connections Made of Cast-in-Place Shear Keys

This work investigates the horizontal and web shear resistance of continuous and discontinuous slab-web connections in pre-cast pre-tensioned bridge systems. The beams were full scale pre-cast pre-tensioned girders and the slabs were made of ordinary reinforced concrete either cast in place, for continuous connections, or pre-cast slabs with holes spaced at 312.5 mm to be set in place, for discontinuous connections. The main variables were the connection type (continuous or discontinuous) and the ratio of the connection steel. From the test results and the numerical analysis performed, a modified stress field for the inclined compressive strut in the truss model is proposed for continuous and discontinuous slab-web connections. The analytical results obtained with the proposed modified stress field in the truss model compared well with the tests results. Design procedures for these types of elements are also discussed.     

Dry Fractionation of Cupuassu (Theobroma grandiflorum) Fat: Physical–Chemical Properties and Polymorphic Behavior

Physical chemical properties of cupuassu fat were modified by dry fractionation. Stearin and olein fractions were obtained at 29, 26, and 24 °C. Polymorphic behavior of unfractionated cupuassu fat (UCF) and its fractions were studied in situ by small-angle (SAXS) and wide-angle (WAXS) X-ray scattering using synchrotron light. Polymorphic transitions were followed in real time tempering samples with a thermal cycle. For UCF, the main polymorphic form crystallized under selected conditions was the β’₂. α and β’₁-forms appeared in trace amounts. β₂-form was obtained after storage at 25 °C for 3 months. Stearins obtained at 26 (S-26) and 24 °C (S-24) showed a similar polymorphic behavior. However, S-26 with improved physical properties might be more suitable for chocolate production or as a trans-fat alternative than UCF. Stearin fraction obtained at 29 °C (S-29) had a complex polymorphic behavior. The α-form was the first polymorphic form detected followed by β’₂-form. There was a polymorphic transition from α to β’₁-form but no transition between β’-forms. They were independent to each other showing fractionation in two different solid solutions. Increased contents of the triacylglycerols (TAG) SOA and SOB together with lower contents of SOO compared to UCF led to co-crystallization because there was no complete compatibility among all TAG present in S-29. β₁-form crystallized after storage forming crystals with a double-layer arrangement and a characteristic morphology. This form could be useful for accelerating crystallization process in melted liquid systems.