Abstract
When real applications are working with automatic speech transcription, the first source of error does not originate from the incoherence in the analysis of the application but from the noise in the automatic transcriptions. This study presents a simple but effective method to generate a new transcription of better quality by combining utterances from competing transcriptions. We have extended a structured Named Entity (NE) recognizer submitted during the ETAPE Challenge. Working on French TV and Radio programs, our system revises the transcriptions provided by making use of the NEs it has detected. Our results suggest that combining the transcribed utterances which optimize the F-measures, rather than minimizing the WER scores, allows the generation of a better transcription for NE extraction. The results show a small but significant improvement of 0.9 % SER against the baseline system on the ROVER transcription. These are the best performances reported to date on this corpus.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
\(WER=\frac{S+D+I}{N}\), where D, I, S stand for the number of deletions, insertions, substitutions of words and N for the total number of words in the reference.
- 2.
More information about the challenge can be found at www.afcp-parole.org/etape/workshop.html.
- 3.
As a first working hypothesis, we have segmented the transcriptions based on the gold standard utterances.
- 4.
References
Dinarelli, M., Rosset, S.: Models cascade for tree-structured named entity detection. In: Proceedings of International Joint Conference on Natural Language Processing (IJCNLP), pp. 1269–1278 (2011)
Favre, B., Béchet, F., Nocéra, P.: Robust named entity extraction from large spoken archives. In: Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP), pp. 491–498 (2005)
Fiscus, J.: A post-processing system to yield reduced word error rates: recognizer output voting error reduction (rover). In: Proceedings IEEE Automatic Speech Recognition and Understanding Workshop, pp. 347–352 (1997)
Goel, V., Byrne, W.: Minimum bayes-risk automatic speech recognition. Comput. Speech Lang. 14(2), 115–135 (2000)
Gravier, G., Adda, G., Paulson, N., Carré, M., Giraudel, A., Galibert, O.: The ETAPE corpus for the evaluation of speech-based TV content processing in the french language. In: International Conference on Language Resources, Evaluation and Corpora (2012)
Gravier, G., Bonastre, J., Geoffrois, E., Galliano, S., McTait, K., Choukri, K.: Ester, une campagne d’évaluation des systèmes d’indexation automatique d’émissions radiophoniques en franais. In: Proceedings Journées d’Etude sur la Parole (JEP) (2004)
Hakkani-Tr, D., Béchet, F., Riccardi, G., Tur, G.: Beyond ASR 1-best: using word confusion networks in spoken language understanding. Comput. Speech Lang. 20, 495–514 (2006)
Jurafsky, D., Martin, J.: Speech and Language Processing. Prentice Hall, Englewood Cliffs (2008)
Kripke, S.: Naming and necessity. In: Davidson, D., Harman, G. (eds.) Semantics of Natural Language. Harvard University Press, Cambridge (1972)
Makhoul, J., Kubala, F., Schwartz, R., Weischedel, R.: Performance measures for information extraction. In: Proceedings of DARPA Broadcast News Workshop, pp. 249–252 (1999)
Marin, A., Kwiatkowski, T., Ostendorf, M., Zettlemoyer, L.: Using syntactic and confusion network structure for out-of-vocabulary word detection. In: Proceedings IEEE Spoken Language Technology Workshop (SLT), pp. 159–164 (2012)
McCallum, A., Li, W.: Early results for named entity recognition with conditional random fields, feature induction and web-enhanced lexicons. In: Proceedings of CoNLL-2013, pp. 188–191 (2013)
Nowozin, S., Lampert, C.: Structured learning and prediction in computer vision. Found. Trends Comput. Graph. Vis. 6, 185–365 (2010)
Palmer, D., Ostendorf, M.: Improving information extraction by modeling errors in speech recognizer output. In: Proceedings of the First International Conference on Human Language Technology Research (2001)
Punyakanok, V., Roth, D., Tau Yih, W., Zimak, D.: Learning and inference over constrained output. In: Proceedings of International Joint Conferences on Artificial Intelligence (2005)
Raymond, C.: Robust tree-structured named entities recognition from speech. In: Proceedings of International Conference on Acoustic Speech and Signal Processing, ICASSP 2013 (2013)
Raymond, C., Fayolle, J.: Reconnaissance robuste d’entités nommées sur de la parole transcrite automatiquement. In: Proceedings of Traitement Automatique des Langues Naturelles (2010)
Rosset, S., Grouin, C., Zweigenbaum, P.: Entités nommées structurées: guide d’annotation quaero. Technical report, LIMSI-Centre national de la recherche scientifique (2011)
Subramaniam, L., Roy, S., Faruquie, T., Negi, S.: A survey of types of text noise and techniques to handle noisy text. In: Proceedings of The Third Workshop on Analytics for Noisy Unstructured Text Data, pp. 115–122 (2009)
Tur, G., Deoras, A., Hakkani-Tr, D.: Semantic parsing using word confusion networks with conditional random fields. In: Proceedings of Interspeech 2013, pp. 2579–2583 (2013)
Acknowledgments
We thank Dr. Abeed Sarker and Dr. Graciela Gonzalez for their helpful comments and remarks.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Weissenbacher, D., Raymond, C. (2015). Tree-Structured Named Entities Extraction from Competing Speech Transcriptions. In: Biemann, C., Handschuh, S., Freitas, A., Meziane, F., Métais, E. (eds) Natural Language Processing and Information Systems. NLDB 2015. Lecture Notes in Computer Science(), vol 9103. Springer, Cham. https://doi.org/10.1007/978-3-319-19581-0_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-19581-0_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19580-3
Online ISBN: 978-3-319-19581-0
eBook Packages: Computer ScienceComputer Science (R0)