Maria-Gabriella Di Benedetto

Maria-Gabriella Di Benedetto, Stefanie Shattuck-Hufnagel, Jeung-Yoon Choi et al.

Modelling the process that a listener actuates in deriving the words intended by a speaker requires setting a hypothesis on how lexical items are stored in memory. This work aims at developing a system that imitates humans when identifying words in running speech and, in this way, provide a framework to better understand human speech processing. We build a speech recognizer for Italian based on the principles of Stevens' model of Lexical Access in which words are stored as hierarchical arrangements of distinctive features (Stevens, K. N. (2002). "Toward a model for lexical access based on acoustic landmarks and distinctive features," J. Acoust. Soc. Am., 111(4):1872-1891). Over the past few decades, the Speech Communication Group at the Massachusetts Institute of Technology (MIT) developed a speech recognition system for English based on this approach. Italian will be the first language beyond English to be explored; the extension to another language provides the opportunity to test the hypothesis that words are represented in memory as a set of hierarchically-arranged distinctive features, and reveal which of the underlying mechanisms may have a language-independent nature. This paper also introduces a new Lexical Access corpus, the LaMIT database, created and labeled specifically for this work, that will be provided freely to the speech research community. Future developments will test the hypothesis that specific acoustic discontinuities - called landmarks - that serve as cues to features, are language independent, while other cues may be language-dependent, with powerful implications for understanding how the human brain recognizes speech.

Maria-Gabriella Di Benedetto, Luca De Nardis

All Italian consonants affected by gemination, that is affricates, fricatives, liquids, nasals, and stops, were analyzed within a project named GEMMA that lasted over a span of about 25 years. Results of the analysis on stops, as published in (Esposito, A., and Di Benedetto, M. G. (1999). "Acoustic and Perceptual Study of Gemination in Italian Stops," The Journal of the Acoustical Society of America, ASA, Vol. 30, pp. 175-185) showed that the main acoustic cue to gemination in Italian was closure duration, while frequency and energy domain parameters were not significantly affected by gemination. This paper - the first of a set of two covering all remaining consonants - addresses nasals and liquids; its companion paper addresses affricates and fricatives. Results on nasals and liquids confirm the findings on stops, in particular that the primary acoustic cue to gemination in Italian is durational in nature and corresponds to a lengthened consonant duration. Results also show an inverse correlation between consonant and pre-consonant vowel durations which is, however, also present when considering singleton vs. geminate word sets separately, indicating a sort of duration compensation between these segments to eventually preserve rhythmical structures; this inverse correlation is reinforced when considering singleton and geminate sets combined. Classification tests of singleton vs. geminate consonants show that, for both nasals and liquids, best classification scores are obtained when consonant duration is used as a classification parameter. Although slightly less performing, the ratio between consonant and pre-consonant vowel durations is also a potential good candidate for automatic classification of geminate vs singleton nasals and liquids in Italian.