Pattern recognition in speech perception research
Keywords:Feature extraction, Pattern recognition, Speech, Automatic speech recognitions, Clustering, Flexible patterns, Logistic models, Logistic regressions, Multinomial logistic regressions, Response factors, Rms errors, Speech perceptions
AbstractThe use of more flexible pattern recognition methods in speech perception research was investigated. The logistic regression and methods imported from automatic speech recognition (ASR) technology was included. The APP scores generated by a NAPP model was expressed in the form of a multinomial logistic regression (MNLR). An initial MNLR analysis was conducted and the response factor comprised the 6 response categories. The clustering patterns of consonant responses suggested a factored solution, whereby judgment log-odds were tuned continuously by only the three factors that include closing place, opening place, and gap duration. a reduced logistic model enforcing the decomposition shows RMS error and modal agreement that are nearly indistinguishable from the full CC model.
How to Cite
Copyright on articles is held by the author(s). The corresponding author has the right to grant on behalf of all authors and does grant on behalf of all authors, a worldwide exclusive licence (or non-exclusive license for government employees) to the Publishers and its licensees in perpetuity, in all forms, formats and media (whether known now or created in the future)
i) to publish, reproduce, distribute, display and store the Contribution;
ii) to translate the Contribution into other languages, create adaptations, reprints, include within collections and create summaries, extracts and/or, abstracts of the Contribution;
iii) to exploit all subsidiary rights in the Contribution,
iv) to provide the inclusion of electronic links from the Contribution to third party material where-ever it may be located;
v) to licence any third party to do any or all of the above.