Connected digit recognition by means of reservoir computing

Azarakhsh Jalalvand, Fabian Triefenbach, David Verstraeten, Jean Pierre Martens

Research output: Contribution to journalConference articlepeer-review

19 Scopus citations

Abstract

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 out-put weights being trainable - we can overcome this disadvantage and yet obtain good accuracy. In this paper, we propose the first reservoir-based connected digit recognition system, and we demonstrate good performance on the Aurora-2 testbed. Since RC is a new technology, we anticipate that our present system is still sub-optimal, and further improvements are possible.

Original languageEnglish (US)
Pages (from-to)1725-1728
Number of pages4
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
StatePublished - 2011
Externally publishedYes
Event12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011 - Florence, Italy
Duration: Aug 27 2011Aug 31 2011

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modeling and Simulation

Keywords

  • Digits
  • Reservoir computing
  • Speech recognition

Fingerprint

Dive into the research topics of 'Connected digit recognition by means of reservoir computing'. Together they form a unique fingerprint.

Cite this