Article

Free access

Automatic discovery of contextual factors describing phonological variation

Authors:

Jeff ShragerAuthors Info & Claims

HLT '89: Proceedings of the workshop on Speech and Natural Language

Pages 284 - 289

https://doi.org/10.3115/100964.101005

Published: 21 February 1989 Publication History

Abstract

In this paper we describe a method for automatically discovering subsets of contextual factors which, taken together, are useful for predicting the <i>realizations</i>, or pronunciations, of English words for continuous speech recognition. A decision tree is used for organizing contextual descriptions of phonological variation. This representation enables us to categorize different realizations according to the context in which they appear in the corpus. In addition, this organization permits us to consider simplifications such as pruning and branch clustering, leading to parsimonious descriptions that better predict allophones in these contexts. We created trees to examine the working assumption that preceding phoneme and following phoneme provide important contexts, as exemplified by the use of triphones in hidden Markov models; our results were in general accordance with the assumption. However, we found that other contexts also play a significant role in phoneme realizations.

References

[1]

L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone, Classification and Regression Trees, Wadsworth International Group, Belmont, CA, 1984.]]

[2]

F. Chen, "The importance of context on the realization of phonemes," J. Acoust. Soc. Am., Suppl. 1, vol. 82, 1987.]]

[3]

P. Chou, Applications of Information Theory to Pattern Recognition and the Design of Decision Trees and Trellises, Doctoral Dissertation, Stanford University, Stanford, CA, June 1988.]]

Digital Library

[4]

Y.-L. Chow, R. Schwartz, S. Roucos, O. Kimball, P. Price, F. Kubala, M. Dunham, M. Krasner, J. Makhoul, "The role of word-dependent coarticulatory effects in a phoneme-based speech recognition system," Proc. IEEE Int. Conf. on Acoust., Speech and Signal Proc., pp. 1593--1596, 1986.]]

[5]

W. Fisher, V. Zue, J. Bernstein, D. Pallett, "An acoustic-phonetic data base," J. Acoust. Soc. Am., Suppl. 1, vol. 81, 1987.]]

[6]

R. Gallager, Information Theory and Reliable Communication, John Wiley and Sons, New York, 1968.]]

Digital Library

[7]

S. Ganapathy and V. Rajaraman, "Information theory applied to the conversion of decision tables to computer programs," Commun. of the ACM, vol. 16, no. 9, pp. 532--539, 1973.]]

Digital Library

[8]

J. Henrichon and K. Fu, "A nonparametric partitioning procedure for pattern classification," IEEE Transactions on Computers, vol. C-18, pp. 604--624, May 1969.]]

[9]

F. Jelinek, "Self-organized language modeling for speech recognition," unpublished, IBM T.J. Watson Research Center, Yorktown Heights, N.Y., 1985.]]

[10]

L. Lamel, R. Kassel, S. Seneff, "Speech database development: design and analysis of the acoustic-phonetic corpus," Proceedings of the DARPA Speech Recognition Workshop, L. Baumann, ed., pp. 100--109, 1986.]]

[11]

K.-F. Lee, Large-Vocabulary Speaker-Independent Continuous Speech Recognition: The SPHINX System, Doctoral Dissertation, Carnegie Mellon University, Pittsburgh, PA, April 1988.]]

Digital Library

[12]

D. Paul, "Speaker stress-resistant continuous speech recognition," Proc. IEEE Int. Conf. on Acoust., Speech and Signal Proc., pp. 283--286, 1988.]]

[13]

J. R. Quinlan, "Induction of decision trees," Machine Learning, Kluwer Academic Publishers, Boston, vol. 1, pp. 1--86, 1986.]]

Digital Library

[14]

J. R. Quinlan, "Generating production rules from decision trees," IJCAI-87, pp. 304--307, 1987.]]

[15]

M. Withgott and S. Bagley, The Variant Pronunciation Rule System, (implementation), Xerox Palo Alto Research Center, Palo Alto, CA, 1987.]]

Cited By

Hwang MHuang XAlleva F(1993)Predicting unseen triphones with senonesProceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II10.5555/1946943.1947030(311-314)Online publication date: 27-Apr-1993
https://dl.acm.org/doi/10.5555/1946943.1947030
Bahl Lde Soutza PGopalakrishnan PNahamoo DPicheny M(1991)Context dependent modeling of phones in continuous speech using decision treesProceedings of the workshop on Speech and Natural Language10.3115/112405.112453(264-269)Online publication date: 19-Feb-1991
https://dl.acm.org/doi/10.3115/112405.112453
Phillips MGlass JZue V(1991)Modelling context dependency in acoustic-phonetic and lexical representationsProceedings of the workshop on Speech and Natural Language10.3115/112405.112414(71-76)Online publication date: 19-Feb-1991
https://dl.acm.org/doi/10.3115/112405.112414
Show More Cited By

Index Terms

Recommendations

Phonological models in automatic speech recognition: invited talk
SigMorPhon '08: Proceedings of the Tenth Meeting of ACL Special Interest Group on Computational Morphology and Phonology

The performance of automatic speech recognition systems varies widely across different contexts. Very good performance can be achieved on single-speaker, large-vocabulary dictation in a clean acoustic environment, as well as on very small vocabulary ...
Automatic recognition of regional phonological variation in conversational interaction

One key aspect of face-to-face communication concerns the differences that may exist between speakers' native regional accents. This paper focuses on the characterization of regional phonological variation in a conversational setting. A new, interactive ...
Automatic analysis of Mandarin accented English using phonological features

The problem of accent analysis and modeling has been considered from a variety of domains, including linguistic structure, statistical analysis of speech production features, and HMM/GMM (hidden Markov model/Gaussian mixture model) model classification. ...

Comments

Information & Contributors

Information

Published In

cover image DL Hosted proceedings

HLT '89: Proceedings of the workshop on Speech and Natural Language

February 1989

289 pages

Publisher

Association for Computational Linguistics

United States

Publication History

Published: 21 February 1989

Qualifiers

Article

Acceptance Rates

Overall Acceptance Rate 240 of 768 submissions, 31%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
278
Total Downloads

Downloads (Last 12 months)26
Downloads (Last 6 weeks)3

Reflects downloads up to 15 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Hwang MHuang XAlleva F(1993)Predicting unseen triphones with senonesProceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: speech processing - Volume II10.5555/1946943.1947030(311-314)Online publication date: 27-Apr-1993
https://dl.acm.org/doi/10.5555/1946943.1947030
Bahl Lde Soutza PGopalakrishnan PNahamoo DPicheny M(1991)Context dependent modeling of phones in continuous speech using decision treesProceedings of the workshop on Speech and Natural Language10.3115/112405.112453(264-269)Online publication date: 19-Feb-1991
https://dl.acm.org/doi/10.3115/112405.112453
Phillips MGlass JZue V(1991)Modelling context dependency in acoustic-phonetic and lexical representationsProceedings of the workshop on Speech and Natural Language10.3115/112405.112414(71-76)Online publication date: 19-Feb-1991
https://dl.acm.org/doi/10.3115/112405.112414
Chen F(1989)Contextually-based data-derived pronunciation networks for automatic speech recognitionProceedings of the workshop on Speech and Natural Language10.3115/1075434.1075494(374-380)Online publication date: 15-Oct-1989
https://dl.acm.org/doi/10.3115/1075434.1075494

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Figures

Tables

Media

View Table of Conten