Description of acoustic variations by hidden Markov models with tree structure
نویسندگان
چکیده
This research was sponsored in part by U S WEST and in part by the Defense Advanced Research Projects Agency (DOD), and monitored by the Space and Naval Warfare Systems Command under Contract N0003985-C-0163, ARPA Order No. 5167. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of U S WEST, DARPA or the US government. K e y w o r d s : HMM(Hidden Markov Model), Binary-Tree Vector Quantization, Decision Tree Clustering, CART, Speaker Clustering, Smoothing.
منابع مشابه
شبکه عصبی پیچشی با پنجرههای قابل تطبیق برای بازشناسی گفتار
Although, speech recognition systems are widely used and their accuracies are continuously increased, there is a considerable performance gap between their accuracies and human recognition ability. This is partially due to high speaker variations in speech signal. Deep neural networks are among the best tools for acoustic modeling. Recently, using hybrid deep neural network and hidden Markov mo...
متن کاملPersian Phone Recognition Using Acoustic Landmarks and Neural Network-based variability compensation methods
Speech recognition is a subfield of artificial intelligence that develops technologies to convert speech utterance into transcription. So far, various methods such as hidden Markov models and artificial neural networks have been used to develop speech recognition systems. In most of these systems, the speech signal frames are processed uniformly, while the information is not evenly distributed ...
متن کاملAn Adaptive Approach to Increase Accuracy of Forward Algorithm for Solving Evaluation Problems on Unstable Statistical Data Set
Nowadays, Hidden Markov models are extensively utilized for modeling stochastic processes. These models help researchers establish and implement the desired theoretical foundations using Markov algorithms such as Forward one. however, Using Stability hypothesis and the mean statistic for determining the values of Markov functions on unstable statistical data set has led to a significant reducti...
متن کاملSelection of Shared-State Hidden Markov Model Structure Using Bayesian Criterion
A Shared-State Hidden Markov Model (SS-HMM) has been widely used as an acoustic model in speech recognition. In this paper, we propose a method for constructing SS-HMMs within a practical Bayesian framework. Our method derives the Bayesian model selection criterion for the SS-HMM based on the variational Bayesian approach. The appropriate phonetic decision tree structure of the SS-HMM is found ...
متن کاملAcoustic modelling of English-accented and Afrikaans-accented South African English
In this paper we investigate whether it is possible to combine speech data from two South African accents of English in order to improve speech recognition in any one accent. Our investigation is based on Afrikaans-accented English and South African English speech data. We compare three acoustic modelling approaches: separate accent-specific models, accentindependent models obtained by straight...
متن کامل