Hierarchical Models for Rescoring Graphs vs. Full Integration

  • Raquel Justo
  • M. Inés Torres
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8258)


In this work, we explore the integration of hierarchical Language Models (HLMs) in different modules of a Spoken Dialog System. First of all, HLMs are integrated into the Automatic Speech Recognition system. In order to carry out this integration, within the recognition process, finite-state machines were considered. This approach was compared to a two step decoding process in which HLMs are used to rescore a graph. Then, HLMs were also used for Language Understanding (LU) purposes. Two architectures were compared theoretically and empirically in both ASR and LU modules.


finite-state machines language models automatic speech recognition language understanding 


  1. 1.
    Caseiro, D., Trancoso, I.: A specialized on-the-fly algorithm for lexicon and language model composition. IEEE TASLP 14(4), 1281–1291 (2006)Google Scholar
  2. 2.
    Chung, E., Jeon, H.B., Park, J.G., Lee, Y.K.: Lattice rescoring for speech recognition using large scale distributed language models. In: Proceedings of COLING, pp. 217–224 (2012)Google Scholar
  3. 3.
    Dolfing, H.J.G.A., Hetherington, I.L.: Incremental language models for speech recognition using finite-state transducers. In: Proceedings of IEEE ASRU, pp. 194–197. Madonna di Campiglio, Italy (2001)Google Scholar
  4. 4.
    GENIO: Gestor Embebido Natural de Interfaz Oral. INTEK project. Industry Department. Basque Government (2006)Google Scholar
  5. 5.
    Justo, R., Pérez, A., Torres, M.I.: Impact of the approaches involved on word-graph derivation from the ASR system. In: Vitrià, J., Sanches, J.M., Hernández, M. (eds.) IbPRIA 2011. LNCS, vol. 6669, pp. 668–675. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  6. 6.
    Justo, R., Torres, M.I.: Phrase classes in two-level language models for asr. Pattern Analysis & Applications 12(4), 427–437 (2009)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Justo, R., Torres, M.I.: Using finite state models for the integration of hierarchical LMS into ASR systems. In: Martínez-Trinidad, J.F., Carrasco-Ochoa, J.A., Ben-Youssef Brants, C., Hancock, E.R. (eds.) MCPR 2011. LNCS, vol. 6718, pp. 332–340. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  8. 8.
    Pereira, F., Riley, M.D.: Speech recognition by composition of weighted finite automata. In: Finite-State Language Processing, pp. 431–453. MIT Press (1996)Google Scholar
  9. 9.
    Rastrow, A., Dredze, M., Khudanpur, S.: Fast syntactic analysis for statistical language modeling via substructure sharing and uptraining. In: Proceedings of ACL 2012, Stroudsburg, PA, USA, pp. 175–183 (2012)Google Scholar
  10. 10.
    Siniscalchi, S.M., Svendsen, T., Lee, C.H.: A bottom-up modular search approach to large vocabulary continuous speech recognition. IEEE TASLP 21(4), 786–797 (2013)Google Scholar
  11. 11.
    Torres, M.I., Casacuberta, F.: Stochastic k-tss bi-languages for machine translation. In: Proceedings of FSMNLP, pp. 98–106. ACL (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Raquel Justo
    • 1
  • M. Inés Torres
    • 1
  1. 1.Dpto. Electricidad y ElectrónicaUniversidad del País Vasco (UPV/EHU)Spain

Personalised recommendations