A Proof-of-Concept for Orthographic Named Entity Correction in Spanish Voice Queries

  • Julián Moreno SchneiderEmail author
  • José Luis Martínez Fernández
  • Paloma Martínez
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8382)


Automatic speech recognition (ASR) systems are not able to recognize entities that are not present in its vocabulary. The problem considered in this paper is the misrecognition of named entities in Spanish voice queries introducing a proof-of-concept for named entity correction that provides alternative entities to the ones incorrectly recognized or misrecognized by retrieving entities phonetically similar from a dictionary. This system is domain-dependent, using sports news, especially football news, regardless of the automatic speech recognition system used. The correction process exploits the query structure and its semantic information to detect where a named entity appears. The system finds the most suitable alternative entity from a dictionary previously generated with the existing named entities.


Automatic speech recognition Audio transcription Question answering Phonetic representation Named entity correction Machine learning 



This work has been partially supported by the Regional Government of Madrid under the Research Network MA2VICMR (S2009/TIC-1542) and by the Spanish Center for Industry Technological Development (CDTI, Ministry of Industry, Tourism and Trade) through the BUSCAMEDIA Project (CEN-20091026).


  1. 1.
    Jeong, M.: Using higher-level linguistic knowledge for speech recognition error correction in a spoken QA dialog. In: Proceedings of the HLT-NAACL Special Workshop on Higher-Level Linguistic Information for Speech Processing, pp. 48–55 (2004)Google Scholar
  2. 2.
    Kaki, S., Eiichiro Sumita, and Hitoshi Iida.: A Method for Correcting Speech Recognition Using the Statistical features of Character Co-occurrence, COLING-ACL’98, 653–657 (1998)Google Scholar
  3. 3.
    Ringger, E.K., Allen, J.F.: A fertility model for post correction of continuous speech recognition ICSLP’96, pp. 897–900 (1996)Google Scholar
  4. 4.
    Sarma, A., Palmer, D.: Context-based speech recognition error detection and correction. In: Proceedings of HLT-NAACL (2004)Google Scholar
  5. 5.
    Ringger, E.K., Allen, J.F.: Error correction via a post-processor for continuous speech recognition. In: Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 427–430, Atlanta, GA (1996)Google Scholar
  6. 6.
    Ogata, J., Goto, M.: Speech repair: quick error correction just by using selection operation for speech input interfaces. In: Proceedings of Eurospeech’05, pp. 133–136 (2005)Google Scholar
  7. 7.
    Reyes-Barragán, A., Villaseñor-Pineda, L., Montes-y-Gómez, M.: Expansión fonética de la consulta para la recuperación de información en documentos hablados. Septiembre, 2011 Procesamiento del Lenguaje Natural, Revista nº 47, pp. 57–64 (2011)Google Scholar
  8. 8.
    Gil, J. Transcripción fonética: Representación escrita de los sonidos que pronunciamos. Fonética para profesores de español: De la teoría a la práctica. p. 547. Arco/Libros (2007)Google Scholar
  9. 9.
    Gusfield, D.: Algorithms on Strings, Trees, and Sequences: Computer Science and Computational Biology. Cambridge University Press, New York (1997)Google Scholar
  10. 10.
    Cohen, W.W., Ravikumar, P., Fienberg, S.E.: A comparison of string distance metrics for name-matching tasks. In: Proceedings of II Web 2003 – IJCAI Workshop on Information Integration on the Web, pp. 73–78 (2003)Google Scholar
  11. 11.
    LivingSpanish: Correspondencia de fonemas y grafías en español. (2011)
  12. 12.
    Fiscus, J.G., Ajot, J., Garofolo, J.S., Doddington, G.: Results of the 2006 spoken term detection evaluation, pp. 45–50 (2007)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Julián Moreno Schneider
    • 1
    Email author
  • José Luis Martínez Fernández
    • 2
  • Paloma Martínez
    • 1
  1. 1.Computer Science DepartmentUniversidad Carlos III de MadridLeganés, MadridSpain
  2. 2.DAEDALUS – Data, Decisions and Language S.a.MadridSpain

Personalised recommendations