Abstract
The conventional methods of automatic text-independent phoneme segmentation detect phoneme boundaries via calculating the acoustic changes along speech signals followed by a peak picking procedure according to user-defined rules. Instead, this paper presents a learning-based method in which the phoneme boundaries are viewed as critical points in the acoustic change context of speech signals. First, we adopt a metric learning procedure in the calculation of acoustic changes, in order to make the acoustic changes at phoneme boundaries more discriminative. Then, latent-dynamic conditional random field is used to model the acoustic change context of speech signals for the detection of phoneme boundaries. The experiments demonstrate that our method outperforms the rule-based methods reported in previous work.
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
Lee, C.-H., et al.: An overview on automatic speech attribute transcription (ASAT). In: Proc. Interspeech, pp. 1825–1828 (2007)
Aversano, G., et al.: A new text-independent method for phoneme segmentation. In: Proc. IEEE Midwest Symposium on Circuits and Systems, vol. 2, pp. 516–519 (2001)
Dusan, S., Rabiner, L.: On the relation between maximum spectral transition positions and phone boundaries. In: Proc. InterSpeech, pp. 17–21 (2006)
Estevan, Y., et al.: Finding maximum margin segments in speech. In: Proc. ICASSP, vol. 4, pp. IV–937 (2007)
Scharenborg, O., et al.: Segmentation of speech: Childs play? In: Proc. International Conference on Spoken Language Processing, pp. 1953–1956 (2007)
Qiao, Y., et al.: Unsupervised optimal phoneme segmentation: objectives, algorithm and comparisons. In: Proc. ICASSP, pp. 3989–3992 (2008)
Qiao, Y., Minematsu, N.: Metric learning for unsupervised phoneme segmentation. In: Proc. Interspeech (2008)
Almpanidis, G., et al.: Robust detection of phone boundaries using model selection criteria with few observations. IEEE Transactions on Audio, Speech, and Language Processing 17(2), 287–298 (2009)
Scharenborg, O., et al.: Unsupervised speech segmentation: An analysis of the hypothesized phone boundaries. The Journal of the Acoustical Society of America 127, 1084 (2010)
Khanagha, V., et al.: Improving text-independent phonetic segmentation based on the microcanonical multiscale formalism. In: Proc. ICASSP, pp. 4484–4487 (2011)
Kuhl, P.K.: Early language acquisition: cracking the speech code. Nature Reviews Neuroscience 5(11), 831–843 (2004)
Morency, L.-P., et al.: Latent-dynamic discriminative models for continuous gesture recognition. In: CVPR, pp. 1–8 (2007)
Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. The Journal of Machine Learning Research 10, 207–244 (2009)
Garofolo, J.S.: TIMIT: acoustic-phonetic continuous speech corpus. Linguistic Data Consortium (1993)
Lafferty, J., et al.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: ICML (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Teng, P., Liu, X., Jia, Y. (2013). Text-Independent Phoneme Segmentation via Learning Critical Acoustic Change Points. In: Sun, C., Fang, F., Zhou, ZH., Yang, W., Liu, ZY. (eds) Intelligence Science and Big Data Engineering. IScIDE 2013. Lecture Notes in Computer Science, vol 8261. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-42057-3_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-42057-3_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-42056-6
Online ISBN: 978-3-642-42057-3
eBook Packages: Computer ScienceComputer Science (R0)