NN-grams: Unifying neural network and n-gram language models for Speech Recognition
This is an incremental improvement for speech recognition systems, combining existing methods to enhance performance.
The paper tackles the problem of improving language models for speech recognition by proposing NN-grams, a hybrid model that integrates n-grams and neural networks, and reports that it outperforms an n-gram model on an Italian speech recognition dictation task.
We present NN-grams, a novel, hybrid language model integrating n-grams and neural networks (NN) for speech recognition. The model takes as input both word histories as well as n-gram counts. Thus, it combines the memorization capacity and scalability of an n-gram model with the generalization ability of neural networks. We report experiments where the model is trained on 26B words. NN-grams are efficient at run-time since they do not include an output soft-max layer. The model is trained using noise contrastive estimation (NCE), an approach that transforms the estimation problem of neural networks into one of binary classification between data samples and noise samples. We present results with noise samples derived from either an n-gram distribution or from speech recognition lattices. NN-grams outperforms an n-gram model on an Italian speech recognition dictation task.