Author name cluster

Nelson Morgan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

1 author row

NeurIPS Conference 1995 Conference Paper

REMAP: Recursive Estimation and Maximization of A Posteriori Probabilities - Application to Transition-Based Connectionist Speech Recognition

Yochai Konig
Hervé Bourlard
Nelson Morgan

In this paper, we introduce REMAP, an approach for the training and estimation of posterior probabilities using a recursive algorithm that is reminiscent of the EM-based Forward-Backward (Liporace 1982) algorithm for the estimation of sequence likelihoods. Al(cid: 173) though very general, the method is developed in the context of a statistical model for transition-based speech recognition using Ar(cid: 173) tificial Neural Networks (ANN) to generate probabilities for Hid(cid: 173) den Markov Models (HMMs). In the new approach, we use local conditional posterior probabilities of transitions to estimate global posterior probabilities of word sequences. Although we still use ANNs to estimate posterior probabilities, the network is trained with targets that are themselves estimates of local posterior proba(cid: 173) bilities. An initial experimental result shows a significant decrease in error-rate in comparison to a baseline system.

PDF Details

NeurIPS Conference 1995 Conference Paper

SPERT-II: A Vector Microprocessor System and its Application to Large Problems in Backpropagation Training

John Wawrzynek
Krste Asanovic
Brian Kingsbury
James Beck
David Johnson
Nelson Morgan

We report on our development of a high-performance system for neural network and other signal processing applications. We have designed and implemented a vector microprocessor and pack(cid: 173) aged it as an attached processor for a conventional workstation. We present performance comparisons with commercial worksta(cid: 173) tions on neural network backpropagation training. The SPERT-II system demonstrates significant speedups over extensively hand(cid: 173) optimization code running on the workstations.

PDF Details

NeurIPS Conference 1992 Conference Paper

Context-Dependent Multiple Distribution Phonetic Modeling with MLPs

Michael Cohen
Horacio Franco
Nelson Morgan
David Rumelhart
Victor Abrash

A number of hybrid multilayer perceptron (MLP)/hidden Markov model (HMM: ) speech recognition systems have been developed in recent years (Morgan and Bourlard. 1990). In this paper. we present a new MLP architecture and training algorithm which allows the modeling of context-dependent phonetic classes in a hybrid MLP/HMM: framework. The new training procedure smooths MLPs trained at different degrees of context dependence in order to obtain a robust estimate of the cootext-dependent probabilities. Tests with the DARPA Resomce Management database have shown substantial advantages of the context-dependent MLPs over earlier cootext(cid: 173) independent MLPs. and have shown substantial advantages of this hybrid approach over a pure HMM approach.

PDF Details

NeurIPS Conference 1992 Conference Paper

Modeling Consistency in a Speaker Independent Continuous Speech Recognition System

Yochai Konig
Nelson Morgan
Chuck Wooters
Victor Abrash
Michael Cohen
Horacio Franco

We would like to incorporate speaker-dependent consistencies, such as gender, in an otherwise speaker-independent speech recognition system. In this paper we discuss a Gender Dependent Neural Network (GDNN) which can be tuned for each gender, while sharing most of the speaker independent parameters. We use a classification network to help generate gender-dependent phonetic probabilities for a statistical (HMM) recogni(cid: 173) tion system. The gender classification net predicts the gender with high accuracy, 98. 3% on a Resource Management test set. However, the in(cid: 173) tegration of the GDNN into our hybrid HMM-neural network recognizer provided an improvement in the recognition score that is not statistically significant on a Resource Management test set.

PDF Details

NeurIPS Conference 1991 Conference Paper

Connectionist Optimisation of Tied Mixture Hidden Markov Models

Steve Renals
Nelson Morgan
Hervé Bourlard
Horacio Franco
Michael Cohen

Issues relating to the estimation of hidden Markov model (HMM) local probabilities are discussed. In particular we note the isomorphism of ra(cid: 173) dial basis functions (RBF) networks to tied mixture density modellingj additionally we highlight the differences between these methods arising from the different training criteria employed. We present a method in which connectionist training can be modified to resolve these differences and discuss some preliminary experiments. Finally, we discuss some out(cid: 173) standing problems with discriminative training.

PDF Details

NeurIPS Conference 1991 Conference Paper

Software for ANN training on a Ring Array Processor

Phil Kohn
Jeff Bilmes
Nelson Morgan
James Beck

Experimental research on Artificial Neural Network (ANN) algorithms requires either writing variations on the same program or making one monolithic program with many parameters and options. By using an object-oriented library, the size of these experimental programs is reduced while making them easier to read, write and modify. An efficient and flexible realization of this idea is Connection(cid: 173) ist Layered Object-oriented Network Simulator (CLONES). CLONES runs on UNIX1 workstations and on the 100-1000 MFLOP Ring Array Processor (RAP) that we built with ANN algorithms in mind. In this report we describe CLONES and show how it is implemented on the RAP.

PDF Details

NeurIPS Conference 1990 Conference Paper

Connectionist Approaches to the Use of Markov Models for Speech Recognition

Hervé Bourlard
Nelson Morgan
Chuck Wooters

Previous work has shown the ability of Multilayer Perceptrons (MLPs) to estimate emission probabilities for Hidden Markov Mod(cid: 173) els (HMMs). The advantages of a speech recognition system incor(cid: 173) porating both MLPs and HMMs are the best discrimination and the ability to incorporate multiple sources of evidence (features, temporal context) without restrictive assumptions of distributions or statistical independence. This paper presents results on the speaker-dependent portion of DARPA's English language Resource Management database. Results support the previously reported utility of MLP probability estimation for continuous speech recog(cid: 173) nition. An additional approach we are pursuing is to use MLPs as nonlinear predictors for autoregressive HMMs. While this is shown to be more compatible with the HMM formalism, it still suffers from several limitations. This approach is generalized to take ac(cid: 173) count of time correlation between successive observations, without any restrictive assumptions about the driving noise.

PDF Details

NeurIPS Conference 1989 Conference Paper

A Continuous Speech Recognition System Embedding MLP into HMM

Hervé Bourlard
Nelson Morgan

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 Posteriori (MAP) probabilities and could thus be embedded as an emission probability estimator in HMMs. By using contextual information from a sliding window on the input frames. we have been able to improve frame or phoneme clas(cid: 173) sification performance over the corresponding performance for Simple Maximum Likelihood (ML) or even MAP probabilities that are esti(cid: 173) mated without the benefit of context. However. recognition of words in continuous speech was not so simply improved by the use of an MLP. and several modifications of the original scheme were necessary for getting acceptable performance. It is shown here that word recognition performance for a simple discrete density HMM system appears to be somewhat better when MLP methods are used to estimate the emission probabilities.

PDF Details