A real-time recurrent error propagation network word recognition system

@article{Robinson1992ARR,
  title={A real-time recurrent error propagation network word recognition system},
  author={Tony Robinson},
  journal={[Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing},
  year={1992},
  volume={1},
  pages={617-620 vol.1}
}
  • T. Robinson
  • Published 23 March 1992
  • Computer Science
  • [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing
A hybrid system using a connectionist model and a Markov model for the DARPA Resource Management task of large-vocabulary multiple-speaker continuous speech recognition is presented. The connectionist model uses internal feedback for context modeling and provides phone state occupancy probabilities for a simple context independent Markov model. The system has been implemented in real-time on a workstation supported by a DSP board. The use of context-independent phone models leads to the… 
View on IEEE
doi.org
26 Citations
Highly Influential Citations
1
Background Citations
6
Methods Citations
1

26 Citations

Citation Type

Citation Type

Stochastic trajectory modeling for speech recognition
  • Y. Gong, J. Haton
  • Computer Science, Physics
    Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing
  • 1994
TLDR
The authors provide an algorithm for sentence recognition based on the modeling of phoneme-based speech units as clusters of trajectories in their parameter space that demonstrated substantially better recognition accuracy, compared to a conventional context-dependent, whole word HMM.
Combining TDNN and HMM in a hybrid system for improved continuous-speech recognition
TLDR
A hybrid continuous-speech recognition system that leads to improved results on the speaker dependent DARPA Resource Management task is presented, based on a combination of normalized neural network output scores with hidden Markov model (HMM) emission probabilities.
Fully Recurrent Neural Networks for PhonemeBased Speech
TLDR
It can be shown that FRNN are powerful and tractable tools to estimate phoneme probabilities and to replace conventional time alignment modules based on viterbi algorithm.
A Statistical Model for an Automatic Procedure to Compress a Word Transcription Dictionary
TLDR
This work studies the compression of the word transcription dictionaries (WTD) into a more compact form to balance the need between flexibility and reliability and develops a statistical model for an automatic procedure to compress a WTD.
A neural network based, speaker independent, large vocabulary, continuous speech recognition system: the WERNICKE project
TLDR
The ESPRITWERNICKE project brings together a number of different groups from Europe and the US and focuses on extending the state-of-the-art for hybrid hidden Markov model/connectionist approaches to large vocabulary, continu-ous speech recognition.
Combining Neural Networks and Hidden Markov Models for Speech Recognition
TLDR
Combining ANN and HMM within a unifying framework is a suitable approach to ASR, which takes benefit from both techniques and overcomes the corresponding limitations.
Phonetic Context-Dependency In a Hybrid ANN/HMM Speech Recognition System
TLDR
This dissertation details the development and implementation of a phonetic context-dependent system specifically for a recurrent neural network HMM hybrid speech recognition system and describes the research behind finding a successful implementation.
Stochastic trajectory modeling and sentence searching for continuous speech recognition
  • Y. Gong
  • Computer Science
    IEEE Trans. Speech Audio Process.
  • 1997
TLDR
A new approach to modeling phoneme-based speech units is proposed, which represents the acoustic observations of a phoneme as clusters of trajectories in a parameter space, and suggests that the stochastic trajectory model provides a more in-depth modeling of continuous speech signals.
A survey of hybrid ANN/HMM models for automatic speech recognition
Acoustic Modeling of Speech Signal using Artificial Neural Network: A Review of Techniques and Current Trends
TLDR
In this chapter various techniques and works on the Artificial Neural Network (ANN) based acoustic modeling are described.
...
1
2
3
...

References

SHOWING 1-10 OF 11 REFERENCES
Continuous speech recognition using multilayer perceptrons with hidden Markov models
  • N. Morgan, H. Bourlard
  • Computer Science
    International Conference on Acoustics, Speech, and Signal Processing
  • 1990
TLDR
A phoneme based, speaker-dependent continuous-speech recognition system embedding a multilayer perceptron (MLP) into a hidden Markov model (HMM) approach is described, which appears to be somewhat better when MLP methods are used to estimate the probabilities.
A recurrent error propagation network speech recognition system
The DARPA 1000-word resource management database for continuous speech recognition
A database of continuous read speech has been designed and recorded within the DARPA strategic computing speech recognition program. The data is intended for use in designing and evaluating…
An Alphanet approach to optimising input transformations for continuous speech recognition
  • J. Bridle, L. Dodd
  • Computer Science
    [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing
  • 1991
The authors extend to continuous speech recognition (CSR) the Alphanet approach to integrating backprop networks and HMM (hidden Markov model)-based isolated word recognition. They present the theory…
A new paradigm for speaker-independent training
  • F. Kubala, R. Schwartz
  • Physics
    [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing
  • 1991
A paradigm for speaker-independent (SI) training of hidden Markov models (HMMs) is presented for continuous speech recognition. The method uses a large amount of speech from a few speakers instead of…
The use of variable frame rate analysis in speech recognition
Continuously variable duration hidden Markov models for automatic speech recognition
Isolated-utterance speech recognition using hidden Markov models with bounded state durations
TLDR
It was found that in the discrete case the recognition rate of HMM/BSD is 9.0%, 6.3%, and 1.9% higher than the conventional HMMs and HMMs with Poisson and gamma distribution state durations, respectively.
Using phoneme duration and energy contour information to improve large vocabulary isolated-word recognition
TLDR
Minimum duration constraints and energy thresholds for phonemes were used to increase the recognition accuracy of an 86000-word speaker-trained isolated word recognizer, improving the accuracy of acoustic recognition and recognition with the language model.
Automatic Speech Recognition: The Development of the Sphinx Recognition System
TLDR
Thank you for downloading automatic speech recognition the development of the sphinx recognition system, which will help people to enjoy a good book with a cup of coffee in the afternoon and end up in malicious downloads.
...
1
2
...