Recurrent neural network language models (RNNLMs) have recently become increasingly popular for many applications including speech recognition. In previous research RNNLMs have normally been trained on well-matched in-domain data. The adaptation of RNNLMs remains an open research area to be explored. In this paper, genre and topic based RNNLM adaptation techniques are investigated for a multi-genre broadcast transcription task. A number of techniques including Probabilistic Latent Semantic Analysis, Latent Dirichlet Allocation and Hierarchical Dirichlet Processes are used to extract show level topic information. These were then used as additional input to the RNNLM during training, which can facilitate unsupervised test time adaptation. Experiments using a state-of-the-art LVCSR system trained on 1000 hours of speech and more than 1 billion words of text showed adaptation could yield perplexity reductions of 8% relatively over the baseline RNNLM and small but consistent word error rate reductions.
Bibliographic reference. Chen, X. / Tan, T. / Liu, Xunying / Lanchantin, Pierre / Wan, M. / Gales, Mark J. F. / Woodland, Philip C. (2015): "Recurrent neural network language model adaptation for multi-genre broadcast speech recognition", In INTERSPEECH-2015, 3511-3515.