A hierarchical point process model for speech recognition
- 1 March 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 4093-4096
- https://doi.org/10.1109/icassp.2008.4518554
Abstract
In this paper, we present a computational framework to engage distinctive feature-based theories of speech perception. Our approach involves: (i) transforming the signal into a collection of marked point processes, each consisting of distinctive feature landmarks determined by statistical learning methods, and (ii) using the temporal statistics of this sparse representation to probabilistically decode the underlying phonological sequence. In order to assess the viability of this approach, we benchmark our performance on broad class recognition against a range of HMM-based approaches using the CMU Sphinx 3 system. We find our system to be competitive with this baseline and conclude by outlining various avenues for future development of our methodology.Keywords
This publication has 6 references indexed in Scilit:
- Template-Based Spike Pattern Identification With Linear Convolution and Dynamic Time WarpingJournal of Neurophysiology, 2007
- Speech segmentation using probabilistic phonetic feature hierarchy and support vector machinesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Toward a model for lexical access based on acoustic landmarks and distinctive featuresThe Journal of the Acoustical Society of America, 2002
- Detecting stop consonants in continuous speechThe Journal of the Acoustical Society of America, 2002
- Acoustic-phonetic speech parameters for speaker-independent speech recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Syntax processing by auditory cortical neurons in the FM–FM area of the mustached batPteronotus parnelliiProceedings of the National Academy of Sciences, 1997