Connected Digit Recognition by Means of Reservoir Computing

  title={Connected Digit Recognition by Means of Reservoir Computing},
  author={Azarakhsh Jalalvand and Fabian Triefenbach and David Verstraeten and Jean-Pierre Martens},
Most automatic speech recognition systems employ Hidden Markov Models with Gaussian mixture emission distributions to model the acoustics. There have been several attempts however to challenge this approach, e.g. by introducing a neural network (NN) as an alternative acoustic model. Although the performance of these so-called hybrid systems is actually quite good, their training is often problematic and time consuming. By using a reservoir – this is a recurrent NN with only the output weights… CONTINUE READING
Highly Cited
This paper has 21 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 13 extracted citations

Engineering Applications of Neural Networks

Communications in Computer and Information Science • 2017
View 5 Excerpts
Highly Influenced

Reservoir Computing Trends

KI - Künstliche Intelligenz • 2012
View 12 Excerpts
Highly Influenced

Acoustic Modeling With Hierarchical Reservoirs

IEEE Transactions on Audio, Speech, and Language Processing • 2013
View 2 Excerpts

Feature enhancement with a Reservoir-based Denoising Auto Encoder

IEEE International Symposium on Signal Processing and Information Technology • 2013
View 1 Excerpt

Model ensemble for an effective on-line reconstruction of missing data in sensor networks

The 2013 International Joint Conference on Neural Networks (IJCNN) • 2013
View 1 Excerpt


Publications referenced by this paper.
Showing 1-10 of 11 references

A generalized framework for compensation of mel-filterbank outputs in feature extraction for robust asr

E.H.C. Choi
Interspeech, 2005, pp. 933–936. • 2005
View 3 Excerpts
Highly Influenced

An application of recurrent neural nets to phone probability estimation

A. Robinson
IEEE Trans. on Neural Networks, vol. 5, pp. 298–305, 1994. • 1994
View 3 Excerpts
Highly Influenced

Exemplar-Based Sparse Representations for Noise Robust Automatic Speech Recognition

IEEE Transactions on Audio, Speech, and Language Processing • 2011
View 2 Excerpts

A Speech Recognition System Based on a Hybrid HMM/SVM Architecture

First International Conference on Innovative Computing, Information and Control - Volume I (ICICIC'06) • 2006
View 2 Excerpts

Similar Papers

Loading similar papers…