Michele Gubian

Joint analysis of f 0 and speech rate with Functional Data Analysis

In this work we propose the use of Functional Data Analysis (FDA) as a powerful methodology to tackle problems where multiple continuous speech parameters have to be analyzed jointly. A production study on contrastive focus placement in Neapolitan Italian is used as illustration. Two features are analyzed, viz. ƒ0 and relative speech rate, both expressed as continuous functions of time. The results show that known facts about the prosody of Neapolitan Italian emerge from the data, but also other interesting local or cross-feature relationships between contour traits appear. Thus, FDA results can be used as guidance in the exploration of speech feature contour shapes, an operation that used to be carried out manually in previous speech research. The capability of jointly analyzing multiple continuous features provides a valuable improvement not only for speech analysis but also for speech re-synthesis.

Analysis of acoustic reduction using spectral similarity measures

Articulatory and acoustic reduction can manifest itself in the temporal and spectral domains. This study introduces a measure of spectral reduction, which is based on the speech decoding techniques commonly used in automatic speech recognizers. Using data for four frequent Dutch affixes from a large corpus of spontaneous face-to-face conversations, it builds on an earlier study examining the effects of lexical frequency on durational reduction in spoken Dutch [Pluymaekers, M. et al. (2005). J. Acoust. Soc. Am. 118, 2561-2569], and compares the proposed measure of spectral reduction with duration as a measure of reduction. The results suggest that the spectral reduction scores capture other aspects of reduction than duration. While duration can--albeit to a moderate degree--be predicted by a number of linguistically motivated variables (such as word frequency, segmental context, and speech rate), the spectral reduction scores cannot. This suggests that the spectral reduction scores capture information that is not directly accounted for by the linguistically motivated variables. The results also show that the spectral reduction scores are able to predict a substantial amount of the variation in duration that the linguistically motivated variables do not account for.

Using Functional Data Analysis for investigating multidimensional dynamic phonetic contrasts

The study of phonetic contrasts and related phenomena, e.g. inter- and intra-speaker variability, often requires to analyse data in the form of measured time series, like f0 contours and formant trajectories. As a consequence, the investigator has to find suitable ways to reduce the raw and abundant numerical information contained in a bundle of time series into a small but sufficient set of numerical descriptors of their shape. This approach requires one to decide in advance which dynamic traits to include in the analysis and which not. For example, a rising pitch gesture may be represented by its duration and slope, hence reducing it to a straight segment, or by a richer coding specifying also whether (and how much) the rising contour is concave or convex, the latter being irrelevant in some context but crucial in others. Decisions become even more complex when a phenomenon is described by a multidimensional time series, e.g. by the first two formants. In this paper we introduce a methodology based on Functional Data Analysis (FDA) that allows the investigator to delegate most of the decisions involved in the quantitative description of multidimensional time series to the data themselves. FDA produces a data-driven parametrisation of the main shape traits present in the data that is visually interpretable, in the same way as slopes or peak heights are. These output parameters are numbers that are amenable to ordinary statistical analysis, e.g. linear (mixed effects) models. FDA is also able to capture correlations among different dimensions of a time series, e.g. between formants F1 and F2. We present FDA by means of an extended case study on diphthong – hiatus distinction in Spanish, a contrast that involves duration, formant trajectories and pitch contours.

Investigating word learning processes in an artificial agent

Researchers in human language processing and acquisition are making an increasing use of computational models. Computer simulations provide a valuable platform to reproduce hypothesised learning mechanisms that are otherwise very difficult, if not impossible, to verify on human subjects. However, computational models come with problems and risks. It is difficult to (automatically) extract essential information about the developing internal representations from a set of simulation runs, and often researchers limit themselves to analysing learning curves based on empirical recognition accuracy through time. The associated risk is to erroneously deem a specific learning behaviour as generalisable to human learners, while it could also be a mere consequence (artifact) of the implementation of the artificial learner or of the input coding scheme. In this paper a set of simulation runs taken from the ACORNS project is investigated. First a look ‘inside the box’ of the learner is provided by employing novel quantitative methods for analysing changing structures in large data sets. Then, the obtained findings are discussed in the perspective of their ecological validity in the field of child language acquisition.