Robust word boundary detection in spontaneous speech using acoustic and lexical cues | IEEE Conference Publication | IEEE Xplore

Robust word boundary detection in spontaneous speech using acoustic and lexical cues


Abstract:

We consider the problem of word boundary detection in spontaneous speech utterances. Acoustic features have been well explored in the literature in the context of word bo...Show More

Abstract:

We consider the problem of word boundary detection in spontaneous speech utterances. Acoustic features have been well explored in the literature in the context of word boundary detection; however, in spontaneous speech of Switchboard-I corpus, we found that the accuracy of word boundary detection using acoustic features is poor (F-score ~ 0.63). We propose a new feature - that captures lexical cues in the context of the word boundary detection problem. We show that including proposed lexical feature along with the usual acoustic features, the accuracy of the word boundary detection improves considerably (F-score ~ 0.81). We also demonstrate the robustness of our proposed feature in presence of different noise levels for additive white and pink noise.
Date of Conference: 19-24 April 2009
Date Added to IEEE Xplore: 26 May 2009
ISBN Information:

ISSN Information:

Conference Location: Taipei, Taiwan
References is not available for this document.

1. INTRODUCTION

Automatic word boundary detection, a topic that has been investigated for several decades, is still an active area of research due to its impact in diverse applications and, the challenging nature of the problem. Initial applications have included detection of the exact word boundaries to assess speech recognition performance and to make recognizers faster. Other, applications of word boundary detection include detecting regions of out of vocabulary (OOV) words and detecting exact boundaries for unknown named entities in speech. Word boundary information can also be helpful for rich transcription of speech such as in detecting emphatic (prominent) words [1].

Select All
1.
Daniel M. Brenier, Jason M. and Daniel Jurafsky, "The detection of emphatic words using acoustic and lexical features," INTERSPEECH, 2005.
2.
Junqua J.-C. Mak B. and Reaves B., "A robust algorithm for word boundary detection in the presence of noise," IEEE Transactions on Speech and Audio Processing, vol. 2, pp. 406-412, February 1994.
3.
S. Rajendran and B. Yegnanarayana, "Word boundary hypothesization for continuous speech in hindi based on f0 patterns," Speech Communication, vol. 18, pp. 21-46, January 1996.
4.
Jiann-Yow Lin Chin-Teng Lin and Gin-DerWu, "A robust word boundary detection algorithm for variable noise-level environment in cars," IEEE Transactions on intelligent transportation systems, vol. 3, pp. 89-101, March 2002.
5.
J. Harrington and M. Cooper, "Word boundary detection in broad class and phoneme strings," Computer Speech and Language, pp. 367-382, 1989.
6.
M. Cettolo and D. Falavigna, "Automatic detection of semantic boundaries based on acoustic and lexical knowledge," 5th International Conference on Spoken Language Processing, 1998.
7.
Abhinav Sethy, Panayiotis Georgiou, and Shrikanth Narayanan, "Text data acquisition for domain-specific language models," In Proceedings of EMNLP, Sydney, Australia, 2006.
8.
B. Ribeiro-Neto R. Baeza-Yates, "Modern information retrieval," New York: ACM Press, Addison-Wesley, 1999.

References

References is not available for this document.