Abstract
The vocabulary used in speech usually consists of two types of words: a limited set of common words, shared across multiple documents, and a virtually unlimited set of rare words, each of which might appear a few times only in particular documents. In most documents, however, these rare words are not seen at all. The first type of words is typically included in the language model of an automatic speech recognizer (ASR) and is thus widely referred to as in-vocabulary (IV). Words of the second type are missing in the language model and thus are called out-of-vocabulary (OOV). However, these words usually carry important information.
We use a hybrid word/sub-word recognizer to detect OOV words occurring in English talks and describe them as sequences of sub-words. We detected about one third of all OOV words, and were able to recover the correct spelling for 26.2% of all detections by using a phoneme-to-grapheme (P2G) conversion trained on the recognition dictionary. By omitting detections corresponding to recovered IV words, we were able to increase the precision of the OOV detection substantially.
This work was partly supported by European project DIRAC (FP6-027787), by Grant Agency of Czech Republic project No. 102/08/0707, Czech Ministry of Education project No. MSM0021630528 and by BUT FIT grant No. FIT-10-S-2.
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
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Burget, L., et al.: Combination of Strongly and Weakly Constrained Recognizers for Reliable Detection of OOVs. In: ICASSP (2008)
Jiang, H.: Confidence Measures for Speech Recognition: A Survey. Speech Communication 45(4), 455–470 (2005)
Bisani, M., Ney, H.: Open Vocabulary Speech Recognition with Flat Hybrid Models. In: Ninth European Conference on Speech Communication and Technology (2005)
Yazgan, A., et al.: Hybrid Language Models for out of Vocabulary Word Detection in Large Vocabulary Conversational Speech Recognition. In: ICASSP (2004)
Szoke, I., Fapso, M., Burget, L., Černocký, J.: Hybrid Word-Subword Decoding for Spoken Term Detection. In: Proc. SSCS 2008: Speech Search Workshop at SIGIR (2008)
Bisani, M., Ney, H.: Joint-Sequence Models for Grapheme-to-Phoneme Conversion. Speech Communication 50(5), 434–451 (2008)
Hain, T., et al.: The 2007 AMI(DA) System for Meeting Transcription. Multimodal Technologies for Perception of Humans, 414–428 (2008)
Deligne, et al.: Language Modeling by Variable Length Sequences: Theoretical Formulation and Evaluation of Multigrams. In: ICASSP, Detroit, MI, pp. 169–172 (1995)
Hazen, T. J., Bazzi, I.: A Comparison and Combination of Methods for OOV Word Detection and Word Confidence Scoring. In: IEEE Intl. Conference on Acoustics, Speech and Signal Processing (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kombrink, S., Hannemann, M., Burget, L., Heřmanský, H. (2010). Recovery of Rare Words in Lecture Speech . In: Sojka, P., Horák, A., Kopeček, I., Pala, K. (eds) Text, Speech and Dialogue. TSD 2010. Lecture Notes in Computer Science(), vol 6231. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15760-8_42
Download citation
DOI: https://doi.org/10.1007/978-3-642-15760-8_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15759-2
Online ISBN: 978-3-642-15760-8
eBook Packages: Computer ScienceComputer Science (R0)