In this article the authors investigated and presented the experiments on the sentence boundaries annotation from Polish speech using acoustic cues as a source of information. The main result of the investigation is an algorithm for detection of the syntactic boundaries appearing in the places of punctuation marks. In the first stage, the algorithm detects pauses and divides a speech signal into segments. In the second stage, it verifies the configuration of acoustic features and puts hypotheses of the positions of punctuation marks. Classification is performed with parameters describing phone duration and energy, speaking rate, fundamental frequency contours and frequency bands. The best results were achieved for Naive Bayes classifier. The efficiency of the algorithm is 52% precision and 98% recall. Another significant outcome of the research is statistical models of acoustic cues correlated with punctuation in spoken Polish.
The objective of the paper is to use the model of Complexity Scales and Licensing (Cyran 2003, 2010) to account for the existence of two prosodic types: ‘syllable’ and ‘word’ languages (Auer 1993, Szczepaniak 2007), which roughly correspond to syllable-timed and stress-timed languages. We will postulate that these categories are not primitive and that many of their phonological characteristics can be derived from simpler mechanisms of licensing. It will be also argued that the phenomenon of contrast plays an important role in prosodic typology and may infl uence syllable structure. Languages use more marked syllabic confi gurations in order to optimise contrast expression. We will carry out an analysis on a simple hypothetical language in order to demonstrate the interdependence of syllabic complexity and the contrastive potential of a syllabic unit.
From multi-dialogue to monologue in spoken Italian: the pragmatic/prosodic basis of multi-dialogue and its transformation in narrative and descriptive monologues – The paper summarizes the Language into Act Theory (L-AcT), according to which spoken texts are analysed and aligned per utterance to the acoustic source. Three stretches of spoken Italian taken from the LABLITA Corpus (multi-dialogue, dialogue, monologue) are described according to L-AcT as regards turn-taking, information structure, and illocution. The above texts are then compared to a short literary excerpt showing the different syntactic architecture of the two language varieties.