Abstract
Dysfluencies are common in spontaneous speech, but these types of events are laborious to recognize by methods used in speech recognition technologies. Speech recognition systems work well with fluent speech, but their accuracy is degraded by dysfluent events. If dysfluent events can be detected from description of their representative features before speech recognition task, statistical models could be augmented with dysfluency detector module. This work introduces our algorithm developed to extract novelty features of complex dysfluencies and derived functions for detecting pure dysfluent events. It uses statistical apparatus to analyze proposed features of complex dysfluencies in spectral domain and in symbolic sequences. With the help of Support vector machines, it performs objective assessment of MFCC features, MFCC based derived features and symbolic sequence based derived features of complex dysfluencies, where our symbolic sequence based approach increased recognition accuracy from 50.2 to 97.6 % compared to MFCC.
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
Abe, S.: Support Vector Machines for Pattern Classification. In: Advances in Pattern Recognition. Springer, London (2010)
Camastra, F., Vinciarelli, A.: Machine Learning for Audio, Image and Video Analysis: Theory and Applications. Springer-Verlag London Limited (2008)
Hamel, L.: Knowledge Discovery with Support Vector Machines. John Wiley & Sons, Inc., Hoboken (2009)
Howell, P., Davis, S., Bartrip, J.: The UCLASS archive of stuttered speech. Journal of Speech, Language, and Hearing Research 52, 556–569 (2009)
Keogh, E., Chakrabarti, K., Pazzani, M., Mehrotra, S.: Dimensionality Reduction for Fast Similarity Search in Large Time Series Databases. Knowledge and Information Systems 3, 263–286 (2001)
Lin, J., Keogh, E., Lonardi, S., Patel, P.: Finding motifs in time series. ACM Special Interest Group on Knowledge Discovery and Data Mining (2002)
Liu, Y., Shriberg, E., Stolcke, A., Harper, M.: Comparing HMM, Maximum Entropy, and Conditional Random Fields for Disfluency Detection. In: Proceedings of the European Conference on Speech Communication and Technology (2005)
Lustyk, T., Bergl, P., Čmejla, R., Vokřál, J.: Change evaluation of Bayesian detector for dysfluent speech assessment. In: International Conference on Applied Electronics 2011, Pilsen, Czech Republic, pp. 231–234 (2011)
Maskey, S., Zhou, B., Gao, Y.: A Phrase-Level Machine Translation Approach for Disfluency Detection Using Weighted Finite State Transducers. In: Interspeech (2006)
Manber, U., Myers, G.: Suffix arrays: A new method for on-line string searches. SIAM J. Comput. 22(5), 935–948 (1993)
Pálfy, J., Pospíchal, J.: Pattern Search in Dysfluent Speech.. In: Proceedings of the IEEE International Workshop on Machine Learning for Signal Processing, Santander, Spain (2012)
Rabiner, L.R., Schafer, R.W.: Introduction to Digital Speech Processing. In: Foundations and Trends in Signal Processing, pp. 1–194 (2007)
Ravi Kumar, K.M., Ganesan, S.: Comparison of Multidimensional MFCC Feature Vectors for Objective Assessment of Stuttered Disfluencies. International Journal of Advanced Networking and Applications 2, 854–860 (2011)
Świetlicka, I., Kuniszyk-Jóźkowiak, W., Smołka, E.: Hierarchical ANN system for stuttering identification.. Computer Speech and Language 27, 228–242 (2013)
Wiśniewski, M., Kuniszyk-Jóźkowiak, W.: Automatic detection and classification of phoneme repetitions using HTK toolkit. Journal of MIT 17 (2011)
Yi, B.-K., Faloutsos, C.: Fast Time Sequence Indexing for Arbitrary Lp Norms. In: Proceedings of the 26th International Conference on Very Large Databases, pp. 385–394 (2000)
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
Pálfy, J., Pospíchal, J. (2013). Algorithms for Dysfluency Detection in Symbolic Sequences Using Suffix Arrays. In: Habernal, I., Matoušek, V. (eds) Text, Speech, and Dialogue. TSD 2013. Lecture Notes in Computer Science(), vol 8082. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40585-3_11
Download citation
DOI: https://doi.org/10.1007/978-3-642-40585-3_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40584-6
Online ISBN: 978-3-642-40585-3
eBook Packages: Computer ScienceComputer Science (R0)