S. Sharifian and S. M. Ahadi,
Volume 23, Issue 2 (1-2005)
Abstract
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results are desirable for small training data, but with increasing training data, the performance improvement reaches the saturation lvel. In this paper, a new approach is introduced that makes use of the advantages of both mentioned techniques to improve the recognition rate. Here, the models with available training data are trained using MAP while
for those with insufficient training data, appropriate prior parameters for MAP estimation are found using MLLR. This technique has yielded better performance in comparison to either MAP or MLLR, in a system based on FARSDAT speech corpus.
N. Mohammadi, B. Lotfi,
Volume 41, Issue 2 (11-2022)
Abstract
The purpose of this study was to improve the erosion behavior of Inconel 625 alloy by plasma transferred arc-deposited stellite6/B4C composite cladding. For this purpose, 5 wt.% of boron carbide was added to the stellite6 clad. Phase analysis and microstructure evaluation were conducted by Optical Microscope, Field Emission Scanning Electron Microscope (FESEM), and Energy-dispersive Spectroscopy (EDS). Solid particle erosion tests with silica particles at 30˚ and 90˚ impact angles were performed to study the erosion behavior. Eroded surfaces were observed by SEM. Investigations showed that the addition of boron carbide particles caused finer microstructure in composite cladding. Moreover, hardness increased with adding boron carbide. Maximum erosion resistance was achieved at 30˚ impact angle. The weight loss of composite cladding were 20 % and 33 % compared to those obtained in Inconel 625 substrate and stellite6 cladding, respectively. The weight loss of the claddings and substrate showed negligible difference at 90˚ impact angle. The dominant mechanism of erosion for composite cladding at 30˚ impact angle was suggested to be cutting and detachment of reinforcing particles. Crater formation was found the predominant mechanism of erosion at 90˚ impact angle.
