Biologically Plausible Speech Recognition with LSTM Neural Nets

Abstract. Long Short-Term Memory (LSTM) recurrent neural networks (RNNs) are local in space and time and closely related to a biological model of memory in the prefrontal cortex. Not only are they more biologically plausible than previous artificial RNNs, they also outperformed them on many artificially generated sequential processing tasks. This encouraged us to apply LSTM to more realistic problems, such as the recognition of spoken digits. Without any modification of the underlying algorithm, we achieved results comparable to state-of-the-art Hidden Markov Model (HMM) based recognisers on both the TIDIGITS and TI46 speech corpora. We conclude that LSTM should be further investigated as a biologically plausible basis for a bottom-up, neural netbased approach to speech recognition.

• Type: Conference
• Year: 2004
• Where: BIOADIT
• Authors: Alex Graves, Douglas Eck, Nicole Beringer, Jürgen Schmidhuber
• Keywords: BIOADIT 2004, Information Management, Long Short-Term Memory, LSTM, Recurrent Neural Networks