12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Connected Digit Recognition by Means of Reservoir Computing

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

Universiteit Gent, Belgium

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 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.

Full Paper

Bibliographic reference.  Jalalvand, Azarakhsh / Triefenbach, Fabian / Verstraeten, David / Martens, Jean-Pierre (2011): "Connected digit recognition by means of reservoir computing", In INTERSPEECH-2011, 1725-1728.