Multi-Span statistical language modeling for large vocabulary speech recognition

The goal of multi-span language modeling is to integrate the various constraints, both local and global, that are present in the language. In this paper, local constraints are captured via the usual n-gram approach, while global constraints are taken into account through the use of latent semantic analysis. An integrative formulation is derived for the combination of these two paradigms, resulting in an entirely data-driven, multi-span framework for large vocabulary speech recognition. Because of the inherent complementarity in the two types of constraints, the performance of the integrated language model compares favorably with the corresponding n-gram performance. Both perplexity and average word error rate gures are reported and discussed.

[1]  Jerome R. Bellegarda,et al.  A novel word clustering algorithm based on latent semantic analysis , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[2]  Mitch Weintraub,et al.  The Hub and Spoke Paradigm for CSR Evaluation , 1994, HLT.

[3]  Michael W. Berry,et al.  Large-Scale Sparse Singular Value Computations , 1992 .

[4]  Jerome R. Bellegarda,et al.  Exploiting both local and global constraints for multi-span statistical language modeling , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[5]  Jerome R. Bellegarda,et al.  A latent semantic analysis framework for large-Span language modeling , 1997, EUROSPEECH.

[6]  Ronald Rosenfeld,et al.  Trigger-based language models: a maximum entropy approach , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[7]  Lalit R. Bahl,et al.  A Maximum Likelihood Approach to Continuous Speech Recognition , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.