Classifying Unprompted Speech by Retraining LSTM Nets

Abstract. We apply Long Short-Term Memory (LSTM) recurrent neural networks to a large corpus of unprompted speech- the German part of the VERBMOBIL corpus. Training first on a fraction of the data, then retraining on another fraction, both reduces time costs and significantly improves recognition rates. For comparison we show recognition rates of Hidden Markov Models (HMMs) on the same corpus, and provide a promising extrapolation for HMM-LSTM hybrids.

• Type: Conference
• Year: 2005
• Where: ICANN
• Authors: Nicole Beringer, Alex Graves, Florian Schiel, Jürgen Schmidhuber
• Keywords: ICANN 2005, Recognition Rates, Recurrent Neural Networks, VERBMOBIL Corpus