Multi-layer perceptrons and probabilistic neural networks for phoneme recognition

نویسندگان

  • Kjell Elenius
  • Hans G. C. Tråvén
چکیده

Phoneme recognition can be viewed as classifying multivariate observations. Multi-layer perceptrons (MLP) and probabilistic neural networks (PNN) approach the decision problem using two complementary models. The MLP models the discriminant surfaces between different phoneme categories, essentially by piece-wise planar approximations, while the PNN approximates class conditional probability densities by a Gaussian mixture and has no explicit model of the discriminants. In the two networks, connection weights correspond to normal vectors and mean values respectively.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

New variant of the Self Organizing Map in Pulsed Neural Networks to Improve Phoneme Recognition in Continuous Speech

Speech recognition has gradually improved over the years, phoneme recognition in particular. Phoneme recognition plays very important role in speech processing. Phoneme strings are basic representation for automatic language recognition and it is proved that language recognition results are highly correlated with phoneme recognition results. Nowadays, many recognizers are based on Artificial ne...

متن کامل

Feature Frame Stacking in RNN-Based Tandem ASR Systems - Learned vs. Predefined Context

As phoneme recognition is known to profit from techniques that consider contextual information, neural networks applied in Tandem automatic speech recognition (ASR) systems usually employ some form of context modeling. While approaches based on multi-layer perceptrons or recurrent neural networks (RNN) are able to model a predefined amount of context by simultaneously processing a stacked seque...

متن کامل

Cooperative supervised and unsupervised learning algorithm for phoneme recognition in continuous speech and speaker-independent context

Neural networks have been traditionally considered as an alternative approach to pattern recognition in general, and speech recognition in particular. There have been much success in practical pattern recognition applications using neural networks including multi-layer perceptrons, radial basis functions, and self-organizing maps (SOMs). In this paper, we propose a system of SOMs based on the a...

متن کامل

A speech recognition method based on the sequential multi-layer perceptrons

-A no vel multi-layer perceptrons ( MLP)-based speech recognition method is proposed in this study. In this method, the dynamic time warping capability o f hidden Markov models ( H M M ) is directly combined with the discriminant based learning of M L P for the sake o f employing a sequence of MLPs (SMLP) as a word recognizer. Each M L P is regarded as a state recognizer to distinguish an acous...

متن کامل

Spatial-temporal Adaptation in Evolving Fuzzy Neural Networks for On-line Adaptive Phoneme Recognition

The paper is a study on a new class of spatial-temporal evolving fuzzy neural network systems (EFuNNs) for on-line adaptive learning, and their applications for adaptive phoneme recognition. The systems evolve through incremental, hybrid (supervised / unsupervised) learning. They accommodate new input data, including new features, new classes, etc. through local element tuning. Both feature-bas...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1993