A New Transform Domain Neural Network for Text-To-Phoneme Mapping

نویسنده

  • JUKKA SAARINEN
چکیده

In this paper, a new Transform Domain implementation of the well known Multilayer Perceptron Neural Network is presented. With the Transform Domain implementation, the input of the Neural Network can be represented in a more compact manner and the elements of the input vector become uncorrelated. The new Transform Domain Multilayer Perceptron (TDMLP) Neural Network is applied for the problem of Text-To-Phoneme (TTP) mapping and it shows better speed of convergence during training than the well known Multilayer Perceptron (MLP) Neural Network while the phoneme accuracy achieved by the new algorithm is comparable with that of the MLP. Key-Words: Transform Domain Neural Network, Text-To-Phoneme Mapping, Multilayer Perceptron Neural Network, Discrete Cosine Transform, Phoneme Accuracy.

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

بهبود عملکرد سیستم بازشناسی گفتار پیوسته بوسیله ویژگی‌های استخراج شده از مانیفولدهای گفتاری در فضای بازسازی شده فاز

The design for new feature extraction methods out of the speech signal and combination of their obtained information is one of the most effective approaches to improve the performance of automatic speech recognition (ASR) system. Recent researches have been shown that the speech signal contains nonlinear and chaotic properties, but the effects of these properties are not used in the continuous ...

متن کامل

Neural networks for text-to-speech phoneme recognition

This paper presents two different artificial neural network approaches for phoneme recognition for text-to-speech applications: Staged Backpropagation Neural Networks and SelfOrganizing Maps. Several current commercial approaches rely on an exhaustive dictionary approach for text-to-phoneme conversion. Applying neural networks for phoneme mapping for text-to-speech conversion creates a fast dis...

متن کامل

GENERATION OF MULTIPLE SPECTRUM-COMPATIBLE ARTIFICIAL EARTHQUAKE ACCELEGRAMS WITH HARTLEY TRANSFORM AND RBF NEURAL NETWORK

The Hartley transform, a real-valued alternative to the complex Fourier transform, is presented as an efficient tool for the analysis and simulation of earthquake accelerograms. This paper is introduced a novel method based on discrete Hartley transform (DHT) and radial basis function (RBF) neural network for generation of artificial earthquake accelerograms from specific target spectrums. Acce...

متن کامل

A Hybrid Approach to Bilingual Text-To-Phoneme Mapping

In this paper, we address the problem of bilingual text-to-phoneme (TTP) mapping in which the phonetic transcription of isolated written words must be found. In general, in the bilingual/multilingual TTP mapping for isolated words, two processing steps are applied to each input word. The language of each word is first identified and then the letters of the word are translated into their phoneti...

متن کامل

Improving Phoneme Sequence Recognition using Phoneme Duration Information in DNN-HSMM

Improving phoneme recognition has attracted the attention of many researchers due to its applications in various fields of speech processing. Recent research achievements show that using deep neural network (DNN) in speech recognition systems significantly improves the performance of these systems. There are two phases in DNN-based phoneme recognition systems including training and testing. Mos...

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 2002