Large vocabulary continuous speech recognition using associative memory and hidden Markov model

Authors:
Zöhre Kara Kayikci;Günter Palm
Affiliations:
Institute of Neural Information Processing, Ulm University, Ulm, Germany;Institute of Neural Information Processing, Ulm University, Ulm, Germany
Venue:
SSIP'08 Proceedings of the 8th conference on Signal, Speech and image processing
Year:
2008

Citing 3
Cited 0

Alpha-nets: a recurrent “neural” network architecture with a hidden Markov model interpretation

Speech Communication - Neurospeech
Connectionist Speech Recognition: A Hybrid Approach

Connectionist Speech Recognition: A Hybrid Approach
On using written language training data for spoken language modeling

HLT '94 Proceedings of the workshop on Human Language Technology

Quantified Score

Hi-index	0.02

Visualization

Abstract

We attempted to improve recognition accuracy, avoiding extensive retraining when the vocabulary is changed or extended, by applying a hidden Markov model and neural associative memory based hybrid approach to continuous speech recognition. In this approach hidden Markov models are used for subword-unit recognition such as syllables. For a given subword-unit sequence a network of neural associative memories generates first spoken single words and then the whole sentence. The fault-tolerance property of neural associative memory enables the system to correctly recognize words although they are not perfectly pronounced or run into each other. The approach are evaluated for TIMIT, and for WSJ1 5k and 20k test sets. The obtained results are encouraging.