In this paper, a two-stage approach for pattern recognition problems of large scale is proposed. The approach consists of two steps, where two new technologies are developed. The first one is a neural network construc...
详细信息
In this paper, a two-stage approach for pattern recognition problems of large scale is proposed. The approach consists of two steps, where two new technologies are developed. The first one is a neural network construction method that can be used to build very complex decision boundaries for difficult pattern classification tasks. The second is a coarse classification method that takes speed and accuracy into consideration at the same time. And the maximum size of the resulted cluster is controlled in order to avoid too much difference among the size of resulted clusters. Recognition of 1000 hand written Chinese characters is used to test the performance of the approach and the results are promising.
The variations of speakers' vocal tract shapes result in the variations of the formant positions and sequentially in the variances of the features extracted from,every frame of speech. In order to remove or reduce...
详细信息
The variations of speakers' vocal tract shapes result in the variations of the formant positions and sequentially in the variances of the features extracted from,every frame of speech. In order to remove or reduce the variations of the formant positions,a speaker adaptation method will be proposed and investigated in this paper which is based on a frequency warp function(fwf).The fwf warps the frequency axis so that the variations can be *** a given speaker,some frequency reference points are selected to help to get this fwf by finding the relationship between the positions of these reference points before and after the *** to the new positions of those reference points for the given speaker,the fwf can then be *** experimental results show that this method reduces the error rate by an average of 14.5%.
A complex process which is difficult to be mathematically expressed can be described by a set of fuzzy inference rules, and fuzzy modeling has been regarded as one of the key problems in fuzzy systems research. A quic...
详细信息
A complex process which is difficult to be mathematically expressed can be described by a set of fuzzy inference rules, and fuzzy modeling has been regarded as one of the key problems in fuzzy systems research. A quick and accurate fuzzy modeling method is presented in accordance with the characteristics of SISO systems. That is, the domain of discourse of the input variable is divided firstly according to the changing degree of the process output while the input variable changes, and based on the above, dividing the total number and the premise parameters of the fuzzy rules can be determined, then because the presented fuzzy model can be expressed as a fuzzy neural network which is a feedforward neural network, so the BP algorithm is applied to obtain the consequent parameters of the fuzzy rules. The effectiveness of the presented fuzzy modeling method and the generalization ability of the fuzzy rules model are demonstrated by a simulation example.
In a recognition system of off-line handwritten Chinese characters, which has a proper recognition rate, improving the recognition rate of similar characters is the key to raising the whole recognition rate. K-L trans...
详细信息
In a recognition system of off-line handwritten Chinese characters, which has a proper recognition rate, improving the recognition rate of similar characters is the key to raising the whole recognition rate. K-L transformation, linear projection, and nonlinear projection are used to visualize the distribution of high-dimension Chinese character vectors. By making comparison experiments between very-similar and very-different Chinese characters, we summarize the distribution characteristic of the high-dimension similar Chinese characters. Utilizing the Mahalanobis distance to measure the similarity of characters and according to the results of statistical experiments, we present a learning algorithm to determine the similar Chinese characters' boundary based on unequal-contraction of dimension.
Due to the excellent ability of dynamically adjusting the observation scope when the analyzing frequency changed,wavelet transform has been successfully applied to the processing of non-stationary speech *** this pape...
详细信息
Due to the excellent ability of dynamically adjusting the observation scope when the analyzing frequency changed,wavelet transform has been successfully applied to the processing of non-stationary speech *** this paper,we use the Wavelet Transform (WT) result and combine it with the traditional CEP vector(CEP-WT) to produce a new feature as the front-end output of Auto Speech Recognition(ASR) *** and experiments of the new feature show that the proposed method can improve the recognition system performance promisingly.*
keyword spotting and utterance verification is widely used in dialog systems. The capability to deal with words out of a vocabulary is an important factor to evaluate a dialog system. This paper presents the dynamic g...
详细信息
keyword spotting and utterance verification is widely used in dialog systems. The capability to deal with words out of a vocabulary is an important factor to evaluate a dialog system. This paper presents the dynamic garbage evaluation approach, which evaluates the confidence of the utterance in speech recognition with strong flexibility. The combination of the dynamic garbage evaluation approach and antikeyword models solves the problem of lack of flexibility of the explicit garbage models and the verification capability of on-line garbage modeling.
Due to the excellent ability of dynamically adjusting the observation scope when the analyzing frequency changed, wavelet transform has been successfully applied to the processing of a non-stationary speech signal. We...
详细信息
Due to the excellent ability of dynamically adjusting the observation scope when the analyzing frequency changed, wavelet transform has been successfully applied to the processing of a non-stationary speech signal. We use the wavelet transform (WT) result and combine it with the traditional CEP vector (CEP-WT) to produce a new feature as the front-end output of an auto speech recognition system. Evaluation and experiments of the new feature show that the proposed method can improve the recognition system performance promisingly.
作者：
Tranzai LeeFang ZhengWenhu WuCenter for Speech Technology
State Key Laboratory of Intelligent Technology and Systems Department of Computer Science and Technology and Systems Department of Computer Science and Technology Tsinghua University Beijing China
The variations of speakers' vocal tract shapes result in the variations of the formant positions and sequentially in the variances of the features extracted from every frame of speech. In order to remove or reduce...
详细信息
The variations of speakers' vocal tract shapes result in the variations of the formant positions and sequentially in the variances of the features extracted from every frame of speech. In order to remove or reduce the variations of the formant positions, a speaker adaptation method is proposed and investigated in this paper which is based on a frequency warp function (f.w.f.). The f.w.f. warps the frequency axis so that the variations can be reduced. For a given speaker, some frequency reference points are selected to help to get this f.w.f. by finding the relationship between the positions of these reference points before and after the warping. According to the new positions of those reference points for the given speaker, the f.w.f. can then be constructed. The experimental results show that this method reduces the error rate by an average of 14.5%.
keywords spotting and utterance verification is widely used in dialog *** capability to deal with the words out of vocabulary is an important factor to evaluate a dialog *** paper presents dynamic garbage evaluation a...
详细信息
keywords spotting and utterance verification is widely used in dialog *** capability to deal with the words out of vocabulary is an important factor to evaluate a dialog *** paper presents dynamic garbage evaluation approach,which evaluates the confidence of the utterance in speech recognition with strong *** combination of dynamic garbage evaluation approach and antikeyword models solves the problem of lack flexibility of the explicit garbage models and the verification capability of on-line garbage modeling.
A stable discrete time tracking control approach based on dynamic inversion using dynamic neural networks (DNNs) is developed in the paper for robotic manipulators with unknown dynamics nonlinearities. Two novel desig...
详细信息
A stable discrete time tracking control approach based on dynamic inversion using dynamic neural networks (DNNs) is developed in the paper for robotic manipulators with unknown dynamics nonlinearities. Two novel design technologies-dynamic inversion constructed by DNNs and the NN variable structure control-are used for adaptive tracking controller design. The robot control law is composed of the dynamic inversion of the DNN system, adaptive compensation and the NN variable structure control (VSC) components. The developed control scheme guarantees the global stability and tracking error convergence of the NN control system. Finally, the control performance of the proposed control approach is illustrated through the comparison studies with robot tracking control approach using static NNs.
暂无评论