Recurrent neural network based language model
Tomáš Mikolov, Martin Karafiát, Lukáš Burget et al. · Interspeech (USB) · 2010
A new recurrent neural network based language model (RNN LM) with applications to speech recognition is presented. Results indicate that it is possible to obtain around 50% reduction of perplexity by using mixture of several RNN LMs, compared to a state of the art backoff language model. Speech recognition experiments show around 18% reduction of word error rate on the Wall Street Journal task when comparing models trained on the same amount of data, and around 5% on the much harder NIST RT05 task, even when the backoff model is trained on much more data than the RNN LM. We provide ample empirical evidence to suggest that connectionist language models are superior to standard n-gram techniques, except their high computational (training) complexity. Index Terms: language modeling, recurrent neural networks, speech recognition
Cited by 5,225 works. doi:10.21437/interspeech.2010-343
Authors
References
- Learning long-term dependencies with gradient descent is difficult
- Finding Structure in Time
- Hierarchical Probabilistic Neural Network Language Model.
- Training neural network language models on very large corpora
- Adaptive Importance Sampling to Accelerate Training of a Neural Probabilistic Language Model
- A Bit of Progress in Language Modeling Extended Version
- A guide to recurrent neural networks and backpropagation
- A joint language model with fine-grain syntactic tags
- The 2005 AMI System for the Transcription of Speech in Meetings
- The AMI System for the Transcription of Speech in Meetings