Factor analysis based VTS and JUD noise estimation and compensation

Model based compensation schemes are a powerful approach for noise robust speech recognition. Recently there have been a number of investigations into adaptive training, and estimating the noise models used for model adaptation. This paper examines the use of EM-based schemes for both canonical models and noise estimation, including discriminative adaptive training. One issue that arises when estimating the noise model is a mismatch between the noise estimation approximation and final model compensation scheme. This paper proposes FA-style compensation where this mismatch is eliminated, though at the expense of a sensitivity to the initial noise estimates. EM-based discriminative adaptive training is evaluated on in-car and Aurora4 tasks. FA-style compensation is then evaluated in an incremental mode on the in-car task. © 2011 IEEE.

Estimation of micro-flora associated with different stages of Macrobrachium rosenbergii (de Man)

The bacterial flora occurring in muscle, haemolymph, hepatopancreas and gill of brood, juveniles, water, eggs, larvae and rearing water were estimated by selective plate count technique for Entrobacteriaceae, Streptococaceae and Vibrionaceae members. The total viable bacterial count was estimated by total plate count technique on nutrient agar. The total viable counts of bacteria were lowest in water from 6.10x10² CFU/mL) and highest in egg (6.06x10super(8) CFU/g). In brood the total counts were varying from 1.62x10² CFU/g in muscle to 2.20x10super(5) CFU/g in gills. In juveniles, the total plate counts were varying from 2.8x10super(4) CFU/g in muscles to 3.67x10 super(8) CFU/g in hepatopancreas. Selective plate counts show that Enterobacteriaceae members dominate in egg and gills of brood and hepatopancreas of juveniles. Vibrios were found to be dominant in water and larvae of rearing tank. Haemolymph of brood was sterile and did not contain any bacteria while muscle of juvenile was having very low count of total viable bacteria.

Multiple pitch estimation using non-homogeneous poisson processes

Novel statistical models are proposed and developed in this paper for automated multiple-pitch estimation problems. Point estimates of the parameters of partial frequencies of a musical note are modeled as realizations from a non-homogeneous Poisson process defined on the frequency axis. When several notes are combined, the processes for the individual notes combine to give a new Poisson process whose likelihood is easy to compute. This model avoids the data-association step of linking the harmonics of each note with the corresponding partials and is ideal for efficient Bayesian inference of unknown multiple fundamental frequencies in a signal. © 2011 IEEE.

Estimation of fishery resources by sonar surveys

The methodology adopted by the Pelagic Fishery Project, Cochin for surveying the surface fish schools with sonar equipment, is described. The estimates of the biomass arrived at from the surveys conducted during 1975-78 are presented.

Estimation of fish production from Hirakud reservoir

A suitable procedure based broadly on stratified random sampling for estimation of fish production from Hirakud reservoir is described. The total fish production for the years 1978 and 1979 from Hirakud reservoir, along with seasonal variation of different species is discussed.

Estimation of yield of dry air bladders from eel fish

The findings are presented of a study conducted to determine a method for the calculation of the yield of dried air bladders of eel from the weight of the whole fish.