@article{3237631,
  abstract     = {{Accurate acoustic modeling is an essential requirement of a state-of-the-art continuous speech recognizer. The Acoustic Model (AM) describes the relation between the observed speech signal and the non-observable sequence of phonetic units uttered by the speaker. Nowadays, most recognizers use Hidden Markov Models (HMMs) in combination with Gaussian Mixture Models (GMMs) to model the acoustics, but neural-based architectures are on the rise again. In this work, the recently introduced Reservoir Computing (RC) paradigm is used for acoustic modeling. A reservoir is a fixed – and thus non-trained – Recurrent Neural Network (RNN) that is combined with a trained linear model. This approach combines the ability of an RNN to model the recent past of the input sequence with a simple and reliable training procedure. It is shown here that simple reservoir-based AMs achieve reasonable phone recognition and that deep hierarchical and bi-directional reservoir architectures lead to a very competitive Phone Error Rate (PER) of 23.1% on the well-known TIMIT task.}},
  author       = {{Triefenbach, Fabian and Jalalvand, Azarakhsh and Demuynck, Kris and Martens, Jean-Pierre}},
  issn         = {{1558-7916}},
  journal      = {{IEEE TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING}},
  keywords     = {{reservoir computing,recurrent neural networks,automatic speech recognition,Acoustic modeling,TIME,NETS,NEURONS,REPRESENTATIONS,PHONEME RECOGNITION,NEURAL-NETWORKS,ECHO STATE NETWORKS,HIDDEN MARKOV-MODELS,AUTOMATIC SPEECH RECOGNITION}},
  language     = {{eng}},
  number       = {{11}},
  pages        = {{2439--2450}},
  title        = {{Acoustic modeling with hierarchical reservoirs}},
  url          = {{http://doi.org/10.1109/TASL.2013.2280209}},
  volume       = {{21}},
  year         = {{2013}},
}

Altmetric

View in Altmetric

Web of Science

Times cited: