Speech recognizers trained in one condition but operating in a different condition degrade in performance. Typical of this situation is when the recognizer is trained under normal conditions but operated in a stressful and noisy environment as in military applications. This paper reports on recognition experiments conducted with a "simulated stress" data base using a baseline algorithm and its modifications. These algorithms perform acceptably well (1 % substitution rate) for a vocabulary of 105 words under normal conditions, but degradeby an order of magnitude under the "stress" conditions. The experiments also show that the speech production variation caused by noise exposure at the ear is far more deleterious than ambient acoustic noise with a noise cancelling microphone.
This paper presents a five level Neutral Point Clamped (NPC) inverter fed IM (Induction Motor) drive for variable speed application. In general the stator current is very highly affected by the harmonic components. It can be affecting the torque to produce high torque ripple in IM at maximum to low speed region. Since the drive performances are depends on mathematical model contains the parameters variations, noise, common mode voltage, flux variation and harmonic levels of the machine. Torque ripples and voltage saturations are the most significant problems in drive application. To overcome this problem the DTFC (direct torque and flux control) technique based five-level neutral-point-clamped (NPC-5L) approach is used. The proposed control scheme uses to stator current error as variable. Through the resistance estimated PI controller rules based the selection of voltage space vector modulation technique is optimized and motor performance level has been improved. The torque & speed are successfully controlled with less torque response. The results are compared and verified with conventional three phases VSI under different control technique by Matlab/Simulink.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.