Volterra Series for Analyzing Mlp Based Phoneme Posterior Probability Estimator

نویسندگان

  • Joel Praveen Pinto
  • G. S. V. S. Sivaram
  • Hynek Hermansky
  • Mathew Magimai-Doss
  • Joel Pinto
چکیده

We present a framework to apply Volterra series to analyze multilayered perceptrons trained to estimate the posterior probabilities of phonemes in automatic speech recognition. The identified Volterra kernels reveal the spectro-temporal patterns that are learned by the trained system for each phoneme. To demonstrate the applicability of Volterra series, we analyze a multilayered perceptron trained using Mel filter bank energy features and analyze its first order Volterra kernels.

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

Hierarchical multilayer perceptron based language identification

Automatic language identification (LID) systems generally exploit acoustic knowledge, possibly enriched by explicit language specific phonotactic or lexical constraints. This paper investigates a new LID approach based on hierarchical multilayer perceptron (MLP) classifiers, where the first layer is a “universal phoneme set MLP classifier”. The resulting (multilingual) phoneme posterior sequenc...

متن کامل

Enhancing Posterior Based Speech Recognition Systems

The use of local phoneme posterior probabilities has been increasingly explored for improving speech recognition systems. Hybrid hidden Markov model / artificial neural network (HMM/ANN) and Tandem are the most successful examples of such systems. In this thesis, we present a principled framework for enhancing the estimation of local posteriors, by integrating phonetic and lexical knowledge, as...

متن کامل

High performance automatic mispronunciation detection method based on neural network and TRAP features

In this paper, we propose a new approach to utilize temporal information and neural network (NN) to improve the performance of automatic mispronunciation detection (AMD). Firstly, the alignment results between speech signals and corresponding phoneme sequences are obtained within the classic GMM-HMM framework. Then, the long-time TempoRAl Patterns (TRAPs) [5] features are introduced to describe...

متن کامل

A Continuous Speech Recognition System Embedding MLP into HMM

Nelson Morgan IntI. Compo Sc. Institute 1947 Center Street. Suite 600 Berkeley. CA 94704. USA We are developing a phoneme based. speaker-dependent continuous speech recognition system embedding a Multilayer Perceptron (MLP) (Le .• a feedforward Artificial Neural Network). into a Hidden Markov Model (HMM) approach. In [Bourlard & Wellekens]. it was shown that MLPs were approximating Maximum a Po...

متن کامل

Grapheme-Based Automatic Speech Recognition Using KL-HMM

The state-of-the-art automatic speech recognition (ASR) systems typically use phonemes as subword units. In this work, we present a novel grapheme-based ASR system that jointly models phoneme and grapheme information using Kullback-Leibler divergence-based HMM system (KL-HMM). More specifically, the underlying subword unit models are grapheme units and the phonetic information is captured throu...

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 2008