Identification of perceptual cues can be very helpful in almost all areas of speech signal processing. Recently, a new methodology called the 3-Dimensional-Deep Search and a visualized intelligible time-frequency computer-based model AI-gram have been introduced for research on the perceptual cues. Based on the technique, the acoustic cues for stop consonants [1], fricative consonants [2] and n...

An important aspect of distinctive feature based approaches to automatic speech recognition is the formulation of a framework for robust detection of these features. We discuss the application of the support vector machines (SVM) that arise when the structural risk minimization principle is applied to such feature detection problems. In particular, we describe the problem of detecting stop cons...

This paper proposes acoustic-phonetic features for classification of place-of-articulation of stop consonants derived from their temporal structures. The speech signal corresponding to a stop is characterized by several temporal features such as sub-band zero-crossings and envelope fits. Classification experiments on the stops from the TIMIT (read speech) and the Buckeye (conversational speech)...

OBJECTIVES To determine how normal-hearing adults (NHA), normal-hearing children (NHC) and children wearing cochlear implants (CI) differ in the perceptual weight given cues for fricative consonants (having a comparatively long static cue and short transition cue) versus stop consonants (having a comparatively short static cue and long transition cue). METHODS Ten NHA, eleven 5- to 8-year-old...

The current project is a case study–and an extension–of the traditional investigation into sound symbolism (Hinton et al., 1994). Several studies have shown that certain sounds evoke images of particular shapes; for example, oral stop consonants are often associated with angular shapes, whereas sonorants (nasals, liquids, and glides) are associated with round shapes (Berlin, 2006; Köhler, 1947)...

The phonetic context has a large effect on stop consonants in a continuous speech signal [1]. Therefore recognition systems that model allophones using context-dependent Hidden Markov Models have been implemented [3]. HMMs have a great ability for the segmentation in the temporal domain [4][6] but have some difficulties in the recognition because the MLE training (Maximum Likelihood Estimation)...

Slope and y-intercepts of locus equations have previously been shown to successfully classify place of articulation for English voiced stop consonants when derived from measurements at vowel onset and vowel midpoint. However, listeners are capable of identifying English voiced stops when less than 30 ms of vowel is presented. The present results show that modified locus equation measurements ma...

In this paper, we present a methodology for combining acoustic-phonetic knowledge with statistical learning for automatic segmentation and classification of continuous speech. At present we focus on the recognition of broad classes vowel, stop, fricative, sonorant consonant and silence. Judicious use is made of 13 knowledge-based acoustic parameters (APs) and support vector machines (SVMs). It ...

This study investigates the effect of sub-phonemic variation in bilabial stop and sibilant fricative consonants on word identification. Recent research suggests that sub-phonemic variation in stop voicing contrasts influences lexical processing. The present study seeks further support for this view by examining listeners’ responses to synthetic speech varying along VOT and fricative place conti...

Speech-training systems providing visual feedback of vocal tract shape are found to be useful for improving vowel articulation. Estimation of vocal tract shape, based on LPC and other analysis techniques, generally fails during stop closures, due to very low signal energy and unavailability of spectral information. Based on estimated area values and line spectrum pair (LSP) coefficients before ...