• Corpus ID: 61058350

Connectionist Speech Recognition: A Hybrid Approach

  title={Connectionist Speech Recognition: A Hybrid Approach},
  author={Herv{\'e} Bourlard and Nelson Morgan},
From the Publisher: Connectionist Speech Recognition: A Hybrid Approach describes the theory and implementation of a method to incorporate neural network approaches into state-of-the-art continuous speech recognition systems based on Hidden Markov Models (HMMs) to improve their performance. In this framework, neural networks (and in particular, multilayer perceptrons or MLPs) have been restricted to well-defined subtasks of the whole system, i.e., HMM emission probability estimation and… 

The 1994 Abbot hybrid connectionist-HMM large vocabulary recognition system.

The emphasis of the paper is on the differences between the 1993 and 1994 versions of the ABBOT system, which includes the utilization of a larger training corpus, the extension of the lexicon, the application of a trigram language model, and the development of a near-realtime single-pass decoder well suited for the hybrid approach.

A New Approach to Hybrid HMM/ANN Speech Recognition using Mutual Information Neural Networks

It is shown that the resulting hybrid system achieves very high recognition rates, which are now already on the same level as the best conventional HMM systems with continuous parameters, and the capabilities of the mutual information neural networks are not yet entirely exploited.

Robust combination of neural networks and hidden Markov models for speech recognition

Experimental results in speaker-independent, continuous speech recognition over Italian digit-strings validate the novel hybrid framework, allowing for improved recognition performance over HMMs with mixtures of Gaussian components, as well as over Bourlard and Morgan's paradigm.

Predictive Connectionist Approach to Speech Recognition

  • B. Petek
  • Computer Science
    Summer School on Neural Networks
  • 2004
This tutorial describes a context-dependent Hidden Control Neural Network architecture for large vocabulary continuous speech recognition that belongs to a family of Hidden Markov Model/Multi-Layer Perceptron (HMM/MLP) hybrids, usually referred to as Predictive Neural Networks.

Tied posteriors: an approach for effective introduction of context dependency in hybrid NN/HMM LVCSR

  • J. RottlandG. Rigoll
  • Computer Science
    2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100)
  • 2000
The approach is based on a standard hybrid connectionist/HMM recognizer, in which the neural nets are trained to estimate the a posteriori probabilities for all phones in each input frame, and the resulting system is called tied posterior.

Hybrid HMM / Neural Network based Speech Recognition in Loquendo ASR

HMM/ANN combines the advantages of both approaches by using an ANN (a multilayer perceptron) to estimate the state dependent observation probabilities of a HMM, instead of Gaussian mixtures, while the temporal aspects of speech are dealt with by left-to-right HMM models.

Modular Neural Networks for Speech Recognition.

A hybrid speech recognition system based on modular neural networks and the state-of-the-art continuous density IIMM speech recognizer JANUS is developed, shown that modularity and the principle of divide-and-conquer applied to neural network learning reduces training times significantly.

Hybrid Models for Automatic Speech Recognition: A Comparison of Classical ANN and Kernel Based Methods

This paper has recalled the hybrid (ANN/HMM) solutions provided in the past for ANNs and applied them to SVMs performing a comparison between them and found that the ANN/H MM system provides better results than the HMM-based system.

Comparison of a new hybrid connectionist-SCHMM approach with other hybrid approaches for speech recognition

  • H. Hutter
  • Computer Science
    1995 International Conference on Acoustics, Speech, and Signal Processing
  • 1995
This approach compared favorably with other proposed hybrid systems and classical approaches on an isolated German digit recognition task over telephone lines, and exhibited the highest recognition rate and followed by an approach using LVQ3 optimization of the codebook.

Continuous speech recognition

The authors focus on a tutorial description of the hybrid HMM/ANN method, which provides a mechanism for incorporating a range of sources of evidence without strong assumptions about their joint statistics, and may have applicability to much more complex systems that can incorporate deep acoustic and linguistic context.



Statistical Inference in Multilayer Perceptrons and Hidden Markov Models with Applications in Continuous Speech Recognition

The statistical use of a particular classic form of a connectionist system, the Multilayer Perceptron (MLP), is described in the context of the recognition of continuous speech.

Continuous Speech Recognition Using Segmental Neural Nets

A hybrid SNN/HMM system has been developed to combine the advantages of both types of approaches and use is made of the N-best paradigm to generate likely phonetic segmentations, which are then scored by the SNN.

A Continuous Speech Recognition System Embedding MLP into HMM

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.

Links Between Markov Models and Multilayer Perceptrons

It is shown theoretically and experimentally that the outputs of the MLP approximate the probability distribution over output classes conditioned on the input, i.e. the maximum a posteriori probabilities.

The HARPY speech recognition system

The HARPY system is the result of an attempt to understand the relative importance of various design choices of two earlier speech recognition systems developed at Carnegie-Mellon University, in which knowledge is represented as a finite state transition network but without the a-priori transition probabilities.

Connectionist probability estimation in the DECIPHER speech recognition system

Results indicate that connectionist probability estimation can improve performance of a context-independent maximum-likelihood-trained HMM system; performance of the connectionist system is close to what can be achieved using (context-dependent) HMM systems of much higher complexity.

Hybrid neural network/hidden Markov model continuous-speech recognition

A hybrid multilayer perceptron (MLP)/hidde arkov model (HMM) speaker-independent continuous-speech recogni-b tion system, in which the advantages of both approaches are combined using MLPs to estimate the state-dependent observation probabilities of an HMM.

Phoneme recognition using time-delay neural networks

The authors present a time-delay neural network (TDNN) approach to phoneme recognition which is characterized by two important properties: (1) using a three-layer arrangement of simple computing

Review of Neural Networks for Speech Recognition

Further work is necessary for large-vocabulary continuous-speech problems, to develop training algorithms that progressively build internal word models, and to develop compact VLSI neural net hardware.

Phoneme recognition: neural networks vs. hidden Markov models vs. hidden Markov models

A time-delay neural network for phoneme recognition that was able to invent without human interference meaningful linguistic abstractions in time and frequency such as formant tracking and segmentation and does not rely on precise alignment or segmentation of the input.