13th Annual Conference of the International Speech Communication Association

Portland, OR, USA
September 9-13, 2012

Efficient Structured Language Modeling for Speech Recognition

Ariya Rastrow, Mark Dredze, Sanjeev Khudanpur

Center for Language and Speech Processing, and Human Language Technology Center of Excellence, Johns Hopkins University, NJ, USA

The structured language model (SLM) of [1] was one of the first to successfully integrate syntactic structure into language models. We extend the SLM framework in two new directions. First, we propose a new syntactic hierarchical interpolation that improves over previous approaches. Second, we develop a general information-theoretic algorithm for pruning the underlying Jelinek-Mercer interpolated LM used in [1], which substantially reduces the size of the LM, enabling us to train on large data. When combined with hill-climbing [2] the SLM is an accurate model, space-efficient and fast for rescoring large speech lattices. Experimental results on broadcast news demonstrate that the SLM outperforms a large 4-gram LM.


  1. C. Chelba and F. Jelinek, “Structured language modeling,” Computer Speech and Language, vol. 14, no. 4, pp. 283–332, 2000.
  2. A. Rastrow, M. Dreyer, A. Sethy, S. Khudanpur, B. Ramabhadran, and M. Dredze, “Hill climbing on speech lattices: A new rescoring framework,” in Proceeding of ICASSP, 2011

Full Paper

Bibliographic reference.  Rastrow, Ariya / Dredze, Mark / Khudanpur, Sanjeev (2012): "Efficient structured language modeling for speech recognition", In INTERSPEECH-2012, 1660-1663.