Abstract
This paper proposes a scheme for analysing speech data inspired by the concept of working memory, it is uses wavelet analysis and unsupervised learning models. The scheme relies on splitting a sound stream in arbitrary chunks and producing feature streams by sequentially analysing each chunk with time-frequency methods. The purpose of this is to precisely detect the time of transitions as well as length of stable acoustic units that occur between them. The procedure uses two feature extraction stages to analyse the audio chunk and two types of unsupervised machine learning models, hierarchical clustering and Self-Organising Maps. The first pass looks at the whole chunk piece by piece looking for speech and silence parts, this stage takes the root mean square, the arithmetic mean, standard deviation from the samples of each piece and classifies the features using hierarchical clustering into speech and non-speech clusters. The second pass looks for stable patterns and transitions at the locations inferred from the results of the first pass, this step uses Harmonic and Daubechies wavelets for coefficient extraction. After the analysis procedures have been completed the chunk advances 2 seconds, the transient and stable feature vectors are saved within SOMs and a new cycle begins on a new chunk.
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
Ostendorf, M.: Moving Beyond the ”Beads-on-a-String” Model of Speech. In: Proc. IEEE ASRU Workshop, pp. 79–84. IEEE Press (1999)
Hsu, A.S., Chater, N., Vitányi, P.M.B.: The probabilistic analysis of language acquisition: Theoretical, computational, and experimental analysis. Cognition 120, 380–390 (2011)
Stouten, V., Demuynck, K., Van Hamme, H.: Discovering Phone Patterns in Spoken Utterances by Non-Negative Matrix Factorization. Signal Processing Letters 15, 131–134 (2008)
Räsänen, O.: A computational model of word segmentation from continuous speech using transitional probabilities of atomic acoustic events. Cognition 120, 149–176 (2011)
Mercado III, E., Myers, C.E., Gluck, M.A.: Modeling auditory cortical processing as an adaptive chirplet transform. Neurocomputing 32-33, 913–919 (2000)
Pinchevar, R., Najaf-Zadeh, H., Thibault, L., Lahdili, H.: Auditory-inspired sparse representation of audio signals. Speech Communication 53, 643–657 (2011)
Gómez-Vilda, P., Ferrández-Vicente, J.M., Rodellar-Biarge, V., Álvarez-Marquina, A., Mazaira-Fernández, L.M., Olalla, R.M., Muñoz-Mulas, C.: Neuromorphic detection of speech dynamics. Neurocomputing 74, 1191–1202 (2011)
Baddeley, A.: Working memory: Looking back and looking forward. Nature Reviews: Neuroscience 4, 829–839 (2003)
Kohonen, T.: The ”neural” phonetic typewriter. Computer 21(3), 11–22 (1988)
Kohonen, T.: The Self-Organising Map. Proceedings of the IEEE 78(7), 1464–1480 (1990)
Daubechies, I.: Ten lectures on wavelets. Society for Industrial and Applied Mathematics (SIAM) (1992) ISBN:0-89871-274-2
Walker, J.S.: A primer on wavelets and their scientific applications. Chapman & Hall (2008) ISBN 978-1-58488-745-4
Newland, D.E.: Harmonic wavelet analysis. Proc. R. Soc.Lond. 443, 203–225 (1993)
Chouetier, G.F., Glass, J.R.: An implementation of rational wavelets and filter design for phonetic classification. IEEE Transactions on Audio, Speech, and Language Processing 15, 939–948 (2007)
Shao, Y., Chang, C.H.: A generalized time-frequency subtraction method for robust speech enhancement based on wavelet filter bank modeling of human auditory system. In: Proc. IEEE Int. Symp. Circuits Syst., pp. 121–124 (2006)
Shao, Y., Chang, C.H.: Bayesian separation with sparsity promotion in perceptual wavelet domain for speech enhancement and hybrid speech recognition. IEEE Transactions on Systems, Man, and Cybernetics 41, 284–293 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Topoleanu, T.S. (2011). On Computational Working Memory for Speech Analysis. In: Travieso-González, C.M., Alonso-Hernández, J.B. (eds) Advances in Nonlinear Speech Processing. NOLISP 2011. Lecture Notes in Computer Science(), vol 7015. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-25020-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-25020-0_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-25019-4
Online ISBN: 978-3-642-25020-0
eBook Packages: Computer ScienceComputer Science (R0)