Statistical Language Model based on a Hierarchical Approach : MCnv - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2001

Statistical Language Model based on a Hierarchical Approach : MCnv


In this paper, we propose a new language model based on dependent word sequences organized in a multi-level hierarchy. We call this model MC$_{n}^{\nu}$, where $n$ is the maximum number of words in a sequence and $\nu$ is the maximum number of levels. The originality of this model is its capacity to take into account dependent variable-length sequences for very large vocabularies. In order to discover the variable-length sequences and to build the hierarchy, we use a set of $233$ syntactic classes extracted from the $8$ French elementary grammatical classes. The MC$_{n}^{\nu}$ model learns hierarchical word patterns and uses them to reevaluate and filter the n-best utterance hypotheses outputted by our speech recognizer MAUD. The model has been trained on a corpus of $43$ million words extracted from a French newspaper and uses a vocabulary of $20000$ words. Tests have been conducted on $300$ sentences. Results achieved $17\%$ decrease in perplexity compared to an interpolated class trigram model. Rescoring the original n-best hypotheses resulted in an improvement of $5\%$ in accuracy.
No file

Dates and versions

inria-00100677 , version 1 (26-09-2006)


  • HAL Id : inria-00100677 , version 1


Imed Zitouni, Kamel Smaïli, Jean-Paul Haton. Statistical Language Model based on a Hierarchical Approach : MCnv. 7th european conference on speech communication and technology - EUROSPEECH 2001, 2001, Aalborg, Denmark, pp.29. ⟨inria-00100677⟩
62 View
0 Download


Gmail Facebook Twitter LinkedIn More