Abstract
In human speech, most boundaries between phones/words are fuzzy. If a time slice which only includes a sole boundary is given, it is possible that the boundary may locate at any frame within the slice. Different boundary locations form several potential observation segments, which should have similar acoustic spaces because of their neighboring trait in time domain. We call them neighboring segments. In this paper, a fast algorithm of parallel processing of neighboring segments is proposed for decoding. Since the decoder can search a bigger pruning threshold in parallel processing, the proposed algorithm is faster than decoding a single segment. This algorithm is successfully integrated into a Segment Model (SM) based Mandarin Large Vocabulary Continuous Speech Recognition (LVCSR) system, and saves approximately 50% decoding time without obvious influence on the recognition accuracy.
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.
References
Ostendorf, M., Roukos, S.: A Stochastic Segment Model for Phoneme Based Continuous Speech Recognition. IEEE Trans. Acoustic. Speech Signal Processing 37(12), 1857–1869 (1989)
Ostendorf, M., Digalakis, V., Kimball, O.: From HMM’s to Segment Models: A Unifled View of Stochastic Modeling for Speech Recognition. IEEE Transactions on Speech Audio Processing 4(5), 360–378 (1996)
Digalakis, V., Ostendorf, M., Rohlicek, J.: Fast Algorithms for Phone Classification and Recognition Using Segment Based Models. IEEE Transactions on Signal Processing 40(12), 2885–2896 (1992)
Tang, Y.: Stochastic Segment Model based Mandarin Speech Recognition. Dissertation Submitted to Institute of Automation. China Academy of Sciences for the Degree of Doctor of Engineering (2006)
Tang, Y., Liu, W.J., Zhang, Y.Y., Xu, B.: A Fast Framework for the Constrained Mean Trajectory Segment Model by Avoidance of Redundant Computation on Segment. International Journal of Computational Linguistics and Chinese Language Processing 11(1), 73–86 (2006)
Young, S., et al.: The HTK Book, Cambridge (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Peng, S., Liu, WJ., Zhang, H. (2009). Accelerating Segment Model Decoding for LVCSR by Parallel Processing of Neighboring Segments. In: Yu, W., He, H., Zhang, N. (eds) Advances in Neural Networks – ISNN 2009. ISNN 2009. Lecture Notes in Computer Science, vol 5552. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01510-6_106
Download citation
DOI: https://doi.org/10.1007/978-3-642-01510-6_106
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01509-0
Online ISBN: 978-3-642-01510-6
eBook Packages: Computer ScienceComputer Science (R0)