THE USE OF RECURRENT NEURAL NETWORKS IN CONTINUOUS SPEECH RECOGNITION

@inproceedings{Robinson1996THEUO,
  title={THE USE OF RECURRENT NEURAL NETWORKS IN CONTINUOUS SPEECH RECOGNITION},
  author={Tony Robinson and Mike Hochberg},
  year={1996}
}
This chapter was written in 1994. Further advances have been made such as: context-dependent phone modelling; forward-backward training and adaptation using linear input transformations. This chapter describes a use of recurrent neural networks (i.e., feedback is incorporated in the computation) as an acoustic model for continuous speech recognition. The form of the recurrent neural network is described along with an appropriate parameter estimation procedure. For each frame of acoustic data… CONTINUE READING
Highly Cited
This paper has 223 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 85 extracted citations

Speech-as-data technologies for personal information devices

Personal and Ubiquitous Computing • 2003
View 4 Excerpts
Method Support
Highly Influenced

High Order Recurrent Neural Networks for Acoustic Modelling

2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) • 2018
View 2 Excerpts

223 Citations

01020'95'00'06'12'18
Citations per Year
Semantic Scholar estimates that this publication has 223 citations based on the available data.

See our FAQ for additional information.