A hierarchical system for word discovery exploiting DTW-based initialization

Walter O, Korthals T, Haeb-Umbach R, Raj B (2013)
In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2013. IEEE: 386-391.

Conference Paper | English

No fulltext has been uploaded

Author
; ; ;
Abstract
Discovering the linguistic structure of a language solely from spoken input asks for two steps: phonetic and lexical discovery. The first is concerned with identifying the categorical subword unit inventory and relating it to the underlying acoustics, while the second aims at discovering words as repeated patterns of subword units. The hierarchical approach presented here accounts for classification errors in the first stage by modelling the pronunciation of a word in terms of subword units probabilistically: a hidden Markov model with discrete emission probabilities, emitting the observed subword unit sequences. We describe how the system can be learned in a completely unsupervised fashion from spoken input. To improve the initialization of the training of the word pronunciations, the output of a dynamic time warping based acoustic pattern discovery system is used, as it is able to discover similar temporal sequences in the input data. This improved initialization, using only weak supervision, has led to a 40% reduction in word error rate on a digit recognition task.
Publishing Year
Conference
ASRU 2013
Location
Olomouc, Tschechien
Conference Date
2013-12-08 – 2013-12-12
PUB-ID

Cite this

Walter O, Korthals T, Haeb-Umbach R, Raj B. A hierarchical system for word discovery exploiting DTW-based initialization. In: IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2013. IEEE; 2013: 386-391.
Walter, O., Korthals, T., Haeb-Umbach, R., & Raj, B. (2013). A hierarchical system for word discovery exploiting DTW-based initialization. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2013, 386-391.
Walter, O., Korthals, T., Haeb-Umbach, R., and Raj, B. (2013). “A hierarchical system for word discovery exploiting DTW-based initialization” in IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2013 (IEEE), 386-391.
Walter, O., et al., 2013. A hierarchical system for word discovery exploiting DTW-based initialization. In IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2013. IEEE, pp. 386-391.
O. Walter, et al., “A hierarchical system for word discovery exploiting DTW-based initialization”, IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2013, IEEE, 2013, pp.386-391.
Walter, O., Korthals, T., Haeb-Umbach, R., Raj, B.: A hierarchical system for word discovery exploiting DTW-based initialization. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2013. p. 386-391. IEEE (2013).
Walter, Oliver, Korthals, Timo, Haeb-Umbach, Reinhold, and Raj, Bhiksha. “A hierarchical system for word discovery exploiting DTW-based initialization”. IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), 2013. IEEE, 2013. 386-391.
This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar