There is a limit of recognition performance for dialogue speech using acoustic models built only with read speech, because various acoustic and linguistic phenomena, which reflect, the characteristics of spontaneous s...
详细信息
There is a limit of recognition performance for dialogue speech using acoustic models built only with read speech, because various acoustic and linguistic phenomena, which reflect, the characteristics of spontaneous speech, are observed in the dialogue speech. In this paper, we investigated the differences of acoustic properties which cause the limit among isolated words, read speech and spontaneous speech. Firstly, the dialogue speech was compared with the read speech through acoustic analyses. Next, the acoustic models were separately built with each of the speech databases. The recognition performance was experimentally evaluated using the acoustic models and the relations of the differences of the performance to those of the acoustic features observed in the analyses were investigated quantitatively. The effectiveness of speaker adaptation was also investigated in the same manner.
This paper deals with the estimation of an unknown process transfer function in the presence of colored measurement noise. A three-step estimation procedure has been previously developed for transfer functions, the de...
详细信息
This paper deals with the estimation of an unknown process transfer function in the presence of colored measurement noise. A three-step estimation procedure has been previously developed for transfer functions, the delay steps and the orders of which are known in advance. The procedure is extended to deal with transfer functions with unknown delay steps and orders. The auto-correlation function of the error between the process output and model output is utilized for evaluating the model fitness. The effectiveness of the proposed method is demonstrated by a simulation study using a sample set of data in MATLAB.
The activated sludge process is a wastewater treatment technique used at sewage disposal plants. The process should be controlled so that the BOD value of an effluent satisfies a certain criterion. The paper deals wit...
详细信息
The activated sludge process is a wastewater treatment technique used at sewage disposal plants. The process should be controlled so that the BOD value of an effluent satisfies a certain criterion. The paper deals with a fuzzy modeling for the activated sludge process. The output of the fuzzy model is the BOD value. Our proposed fuzzy inference method is applied to the fuzzy model. Since the inferred conclusion using the proposed method has a membership function of simple shape, its meaning can be interpreted easily. Moreover, it can also be considered as a possibility distribution. In addition, its linguistic meaning is interpretable by means of labeling of the membership function with its linguistic term. Since the fuzzy rules of the model consist of labeled fuzzy sets in an antecedent part and also a consequent part, the input-output relation of the process becomes able to be easily understood. The operator can predict a possibility distribution of a future BOD value by simulation with the model, and can take appropriate judgement and control based on the prediction. In the paper, from the modeling result, the effectiveness of the proposed method and the fuzzy model are shown.
In this paper, we propose a method to detect a road sign from a road scene image in the daytime. In order to utilize the color feature of the sign efficiently, the color distribution of sign is examined, and then a co...
详细信息
In this paper, we propose a method to detect a road sign from a road scene image in the daytime. In order to utilize the color feature of the sign efficiently, the color distribution of sign is examined, and then a color similarity map is constructed. Assuming that the color distribution is a normal distribution, a color similarity map is obtained. Additionally, the color similarity shown on the map is incorporated into an image function of an active net model. A road sign is extracted as if it is wrapped up in an active net. Some experimental results obtained by applying an active net to images are presented.
This paper presents an adaptive control scheme for nonlinear systems based on a quasi-ARMAX prediction model that is a specially constructed associative memory network consisting of multiple neurofuzzy models and is d...
详细信息
This paper presents an adaptive control scheme for nonlinear systems based on a quasi-ARMAX prediction model that is a specially constructed associative memory network consisting of multiple neurofuzzy models and is distinctive to usual neural networks in that it is linear in both the parameters to be estimated and the input variables to be synthesized in a control system. This advantage is taken to develop a nonlinear adaptive control scheme similarly to linear one.
This paper proposes an efficient and convenient approach to frequency domain subspace identification for continuous-time systems. In the case of continuous-time models, the data matrices often become ill-conditioned i...
详细信息
This paper proposes an efficient and convenient approach to frequency domain subspace identification for continuous-time systems. In the case of continuous-time models, the data matrices often become ill-conditioned if we simply rewrite the Laplace operator s as s = jw where w denotes the frequency. To avoid the ill-conditioned problem, the operator w = ( s - b.α)/( s + b.α) is introduced such that the system can be identified based on a state-space model in the w -operator. And then the estimated w -operator state-space model can be transformed back to the common continuous-time state-space model. An instrumental variable matrix in the frequency domain is also proposed to obtain consistent estimate in the presence of measurement noise.
Learning automata select an action from a finite set of their available actions and update their strategy on the basis of response received from the random environment using what is known as a reinforcement scheme. As...
详细信息
Learning automata select an action from a finite set of their available actions and update their strategy on the basis of response received from the random environment using what is known as a reinforcement scheme. As an environment changes, the ordering of the actions with performance criterion may vary. If a learning automaton with a fixed strategy is used in such an environment, it may become less expedient with time and even inexpedient. However, using the learning scheme that has sufficient flexibility to track the better actions makes the performance improved. In this paper, a variable structure learning automaton network with periodic random environment is proposed. The results of some numerical simulations show that our model can be used for tracking some periodic nonstationary environment for which an upper bound on the period is known.
This paper provides new combinatorial bounds and characterizations of authentication codes (A-codes) and key predistribution schemes (KPS). We first prove a new lower bound on the number of keys in an A-code without s...
详细信息
This paper provides new combinatorial bounds and characterizations of authentication codes (A-codes) and key predistribution schemes (KPS). We first prove a new lower bound on the number of keys in an A-code without secrecy, which can be thought of as a generalization of the classical Rao bound for orthogonal arrays. We also prove a new lower bound on the number of keys in a general A-code, which is based on the Petrenjuk, Ray-Chaudhuri and Wilson bound for t-designs. We also present new lower bounds on the size of keys and the amount of users' secret information in KPS, the latter of which is accomplished by showing that a certain A-code is `hiding' inside any KPS.
Light adaptive algorithms/architectures are proposed for regularization vision chips. The adaptation mechanisms allow the regularization parameters to change in an adaptive manner in accordance with the light intensit...
详细信息
暂无评论