Speech recognition based on estimation of mutual information
نویسندگان
چکیده
This paper proposed a pattern matching algorithm based on estimation of mutual information for speech recognition. The preliminary experiments on connected Chinese digits recognition show 97% of test digits were recognized correctly with 4 times much less time consume than DTW or HMM, and it was 6% higher than which gotten by conventional DTW with same experiments data and condition. According to our experiments, the proposed algorithm can be considered as an applicable effective matching method for speech recognition especially for monosyllable word recognition.
منابع مشابه
An Information-Theoretic Discussion of Convolutional Bottleneck Features for Robust Speech Recognition
Convolutional Neural Networks (CNNs) have been shown their performance in speech recognition systems for extracting features, and also acoustic modeling. In addition, CNNs have been used for robust speech recognition and competitive results have been reported. Convolutive Bottleneck Network (CBN) is a kind of CNNs which has a bottleneck layer among its fully connected layers. The bottleneck fea...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملSpeaker Adaptation in Continuous Speech Recognition Using MLLR-Based MAP Estimation
A variety of methods are used for speaker adaptation in speech recognition. In some techniques, such as MAP estimation, only the models with available training data are updated. Hence, large amounts of training data are required in order to have significant recognition improvements. In some others, such as MLLR, where several general transformations are applied to model clusters, the results ar...
متن کاملImplementing and Improving MMIE Training in SphinxTrain
Discriminative training schemes, such as Maximum Mutual Information Estimation (MMIE), have been used to improve the accuracy of speech recognition systems trained using Maximum Likelihood Estimation (MLE). In this paper, we present the implementation details of MMIE training in SphinxTrain and baseline results for MMIE training on the Wall Street Journal (WSJ) SI84 and SI284 data sets. This pa...
متن کاملDictionary-based discriminative HMM parameter estimation for continuous speech recognition systems
The estimation of the HMM parameters has always been a major issue in the design of speech recognition systems. Discriminative objectives like Maximum Mutual Information (MMI) or Minimum Classi cation Error (MCE) have proved to be superior over the common Maximum Likelihood Estimation (MLE) in cases where a robust estimation of the probabilistic density functions (pdfs) is not possible. The det...
متن کامل