Current Search: regression testing (x)
View All Items
(1 - 2 of 2)
- Title
- AUTOMATED REGRESSION TESTING APPROACH TO EXPANSION AND REFINEMENT OF SPEECH RECOGNITION GRAMMARS.
- Creator
-
Dookhoo, Raul, DeMara, Ronald, University of Central Florida
- Abstract / Description
-
This thesis describes an approach to automated regression testing for speech recognition grammars. A prototype Audio Regression Tester called ART has been developed using Microsoft's Speech API and C#. ART allows a user to perform any of three tasks: automatically generate a new XML-based grammar file from standardized SQL database entries, record and cross-reference audio files for use by an underlying speech recognition engine, and perform regression tests with the aid of an oracle...
Show moreThis thesis describes an approach to automated regression testing for speech recognition grammars. A prototype Audio Regression Tester called ART has been developed using Microsoft's Speech API and C#. ART allows a user to perform any of three tasks: automatically generate a new XML-based grammar file from standardized SQL database entries, record and cross-reference audio files for use by an underlying speech recognition engine, and perform regression tests with the aid of an oracle grammar. ART takes as input a wave sound file containing speech and a newly created XML grammar file. It then simultaneously executes two tests: one with the wave file and the new grammar file and the other with the wave file and the oracle grammar. The comparison result of the tests is used to determine whether the test was successful or not. This allows rapid exhaustive evaluations of additions to grammar files to guarantee forward process as the complexity of the voice domain grows. The data used in this research to derive results were taken from the LifeLike project. However, the capabilities of ART extend beyond LifeLike. The results gathered have shown that using a person's recorded voice to do regression testing is as effective as having the person do live testing. A cost-benefit analysis, using two published equations, one for Cost and the other for Benefit, was also performed to determine if automated regression testing is really more effective than manual testing. Cost captures the salaries of the engineers who perform regression testing tasks and Benefit captures revenue gains or losses related to changes in product release time. ART had a higher benefit of $21461.08 when compared to manual regression testing which had a benefit of $21393.99. Coupled with its excellent error detection rates, ART has proven to be very efficient and cost-effective in speech grammar creation and refinement.
Show less - Date Issued
- 2008
- Identifier
- CFE0002437, ucf:47703
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0002437
- Title
- Mathematical Modeling of Heart Rate Deflection Point in Relation to Respiratory Compensation and Treadmill Running Performance.
- Creator
-
Baker, Kayla, Fukuda, David, Hoffman, Jay, Stout, Jeffrey, University of Central Florida
- Abstract / Description
-
Heart rate deflection point (HRDP), identified as the second breakpoint in the (")intensity / heart rate(") relationship, is indicative of the anaerobic threshold (AT). This point can be determined via bi-segmental linear regression (2SEG) or through use of the maximal distance model (D-max); however, the relationship between these methods has yet to be investigated 2. Purpose: To compare the use of 2SEG and D-max methods to determine HRDP and to examine the relationship between these values...
Show moreHeart rate deflection point (HRDP), identified as the second breakpoint in the (")intensity / heart rate(") relationship, is indicative of the anaerobic threshold (AT). This point can be determined via bi-segmental linear regression (2SEG) or through use of the maximal distance model (D-max); however, the relationship between these methods has yet to be investigated 2. Purpose: To compare the use of 2SEG and D-max methods to determine HRDP and to examine the relationship between these values with a metabolic threshold, respiratory compensation point (RCP), as well as running performance [5,000 meter treadmill time trial (5Ktime)]. Methods: Nineteen recreationally active men (n=9, 25.56(&)#177;3.17 y, 1.77(&)#177;0.05 m, 83.52(&)#177;6.77 kg, 48.98(&)#177;7.37 ml(&)#183;kg(&)#183;min-1) and women (n=10, 22.78(&)#177;2.11 y, 1.64(&)#177;0.07 m, 62.28(&)#177;6.20 kg, 42.32(&)#177;4.13 ml(&)#183;kg(&)#183;min-1) were recruited for this study. Participants completed two experimental trials, consisting of a graded exercise test to exhaustion (GXT) and 5,000m time trial on the treadmill. Estimates of HRDP and RCP were calculated from data collected during the GXT. One-way repeated measures analysis of variance was used to compare HRDP found through 2SEG (HRDP2SEG), HRDP found through D-max (HRDPD-max), and RCP. Pearson product moment correlations were used to examine the relationship between variables (HRDP2SEG, HRDPD-max, RCP, and 5Ktime). Results: No differences were found between HRDP2SEG (176.70(&)#177;9.40 bpm), HRDPD-max (178.18(&)#177;6.85 bpm), and RCP (176.92(&)#177;6.63 bpm) (p = 0.533). Strong correlations were found between HRDP2SEG and HRDPD-max (r = 0.831, p (<) 0.0001), RCP and HRDP2SEG (r = 0.650, p = 0.003), and RCP and HRDPD-max (r = 0.619, p = 0.005). No relationship was found between 5Ktime and HRDP2SEG (r = 0.419, p = 0.074), HRDPD-max (r = 0.241, p = 0.321), or RCP (r = 0.193, p = 0.429). Similar limits of agreement were found for all comparisons (HRDP2SEG and RCP, p = 0.070; HRDPD-max and RCP, p = 0.868; HRDP2SEG and HRDPD-max, p = 0.029), however, systematic bias was found between HRDP2SEG and HRDPD-max. Conclusion: Based on these results, HRDP2SEG and HRDPD-max could potentially be used interchangeably as methods to determine HRDP. However, the potential for systematic bias must be taken into consideration. Additionally, the results indicate that RCP and HRDP may provide similar estimates of the anaerobic threshold, but none of these thresholds appear to be related to 5Ktime on a treadmill.
Show less - Date Issued
- 2016
- Identifier
- CFE0006070, ucf:50944
- Format
- Document (PDF)
- PURL
- http://purl.flvc.org/ucf/fd/CFE0006070
