Can I read The Use of Recurrent Neural Networks in Continuous Speech Recognition on EtoBox?

The Use of Recurrent Neural Networks in Continuous Speech Recognition by Robinson T., Hochberg M., Renals S. is a nonfiction available to read on EtoBox.

What is The Use of Recurrent Neural Networks in Continuous Speech Recognition about?

Издательство Cambridge University Engineering Department, 1995. -46 pp. Most - if not all - automatic speech recognition systems explicitly or implicitly compute a score (equivalently, distance, probability, etc.) indicating how well a novel utterance matches a model of the hypothesised utterance. A fundamental problem in speech recognition is how this score may be computed, given that speech is a non-stationary stochastic process. In the interest of reducing the computational complexity, the standard approach used in the most prevalent systems (e.g., dynamic time warping (DTW) and hidden Markov models (HMMs)) factors the hypothesis score into a local acoustic score and a local transition score. In the HMM framework, the observation term models the local (in time) acoustic signal as a stationary process, while the transition probabilities are used to account for the time-varying nature of speech. This chapter presents an extension to the standard HMM framework which addresses the issue of the observation probability computation. Specifically, an artificial recurrent neural network (RNN) is used to compute the observation probabilities within the HMM framework. This provides two en

Who reads The Use of Recurrent Neural Networks in Continuous Speech Recognition?

Author

Robinson T., Hochberg M., Renals S.

Language

EN

Category

nonfiction

Subjects

Computer Science, Cybernetics, Stem