We introduce a novel italian language resource for the study of reading and comprehension in aging populations, combining behavioural and linguistic data from healthy controls (HC), individuals with subjective cognitive decline (SCI), participants with Mild Cognitive Impairment (MCI), and patients with mild dementia (CDR1). Reading performance was recorded through a finger-tracking based application during both silent and oral reading, enabling fine-grained temporal analyses at the text, token and character level. Comprehension was assessed via multiple question types (wh-, inferential, referential, and lexical). Descriptive and non-linear regression analyses informed a feature selection process, yielding temporal and comprehension-based measures that capture individual reading dynamics. These features were explored through unsupervised clustering and supervised classification to investigate their discriminative and predictive potential across cognitive profiles. The resource supports research on reading and cognitive decline, offers a reproducible protocol for large-scale data collection, and provides a foundation for developing early cognitive screening and monitoring tools or aging populations.

The Prediction and Recognition of Cognitive Decline through Spontaneous Speech (PROCESS) Signal Processing Grand Challenge focuses on detecting dementia by analyzing spontaneous speech production. The challenge proposes a classification task to distinguish between subjects categorized as healthy controls, mild cognitive impairment, and dementia. Our team tackled this task by leveraging Digital Linguistic Biomarkers (DLBs) extracted from speech. Our system outperformed over 100 competing systems, earning us first place in the classification task.

Digital Linguistic Biomarkers extracted from spontaneous language productions proved to be very useful for the early detection of various mental disorders. This paper presents a computational pipeline for the automatic processing of oral and written texts: the tool enables the computation of a rich set of linguistic features at the acoustic, rhythmic, lexical, and morphosyntactic levels. Several applications of the instrument - for the detection of Mild Cognitive Impairments, Anorexia Nervosa, and Developmental Language Disorders - are also briefly discussed.

This paper presents contributions in two directions: first we propose a new system for Frame Identification (FI), based on pre-trained text encoders trained discriminatively and graphs embedding, producing state of the art performance and, second, we take in consideration all the extremely different procedures used to evaluate systems for this task performing a complete evaluation over two benchmarks and all possible splits and cleaning procedures used in the FI literature.

This paper presents a new approach for building Language Models using the Quantum Probability Theory, a Quantum Language Model (QLM).It mainly shows that relying on this probability calculus it is possible to build stochastic models able to benefit from quantum correlations due to interference and entanglement.We extensively tested our approach showing its superior performances, both in terms of model perplexity and inserting it into an automatic speech recognition evaluation setting, when compared with state-of-theart language modelling techniques.

International audience

Prosodic prominence denotes the perceptual salience of linguistic units. There exists no agreement on (1) ade-quate methods for its subjective measurement, (2) its ob-jective acoustic correlates and (3) its relationship to lin-guistic structure. A traditional approach for evaluating any of these descriptive layers is an inter-level compari-son, e.g. between a perceptual and an acoustic model of prominence. However, (1) there exists no standard pro-cedure for such a comparison, and (2) such a comparison is misleading if both layers are expected to be symmetri-cal, given the neglected influence of linguistic top-down expectancies. We propose an evaluation procedure for prominence models relying on tripartite correlations of perception, its acoustic correlates and linguistic expecta-tions. We suggest a novel correlation metric and test its usefulness on a prosodic corpus of German. Index Terms: prominence, evaluation, prosody 1. Introduction: Model

This paper describes the development and evaluation of a\nprosody prediction module for unit selection speech synthesis that is based on the notion of perceptual prominence. We outline the design principles of the module and describe its implementation in the Bonn Open Synthesis System (BOSS).\nMoreover, we report results of perception experiments that\nhave been conducted in order to evaluate prominence\nprediction. The paper is concluded by a general discussion of the approach and a sketch of perspectives for further work.

Semantic search engines rely on the existence of a rich set of semantic connections between the concepts associated to documents and those used for the queries. With folksonomies, this is not always guaranteed. Creating clusters of folksonomic tags around terms of controlled ontological vocabularies is a potentially sophisticated approach, but algorithms abound for this clustering and no clear cut winner exists. In this paper we introduce FolksEngine, a parametric search engine for folksonomies allowing to specify any clustering algorithm as a three step process: the user’s query is expanded according to semantic rules associated to the terms of the query, the new query is then executed on the plain folksonomy search engine, and the results are ranked according to semantic rules associated to the folksonomic tags actually used for the documents.

Perceptual prominence is an important indicator of a word's and syllable's lexical, syntactic, \nsemantic and pragmatic status in a discourse. Its automatic annotation would be a valuable \nenrichment of large databases used in unit selection speech synthesis and speech recognition. \nWhile much research has been carried out on the interaction between prominence and \nacoustic factors, little progress has been made in its automatic annotation. Previous \napproaches to German relied on linguistic features in prominence detection, but a purely \nacoustic method would be advantageous. We applied an algorithm to German data that had \nbeen previously used for English and Italian. Both the algorithm and the data annotation \nencode prominence as a continuous rather than a categorical parameter. First results are \nencouraging, but again show that prominence perception relies on linguistic expectancies as \nwell as acoustic patterns. Also, our results further strengthen the view that force accents are a \nmore reliable cue to prominence than pitch accents in German.

This paper presents a follow up of a study on the automatic detection of prosodic prominence in continuous speech. Prosodic prominence involves two different prosodic features, pitch accent and stress, that are typically based on four acoustic parameters: fundamental frequency (F0) movements, overall syllable energy, syllable nuclei duration and mid-tohigh-frequency emphasis. A careful measurement of these acoustic parameters, as well as the identification of their connection to prosodic parameters, makes it possible to build an automatic system capable of identifying prominent syllables in utterances with performance comparable with the inter-human agreement reported in the literature. This automatic system has been used to cast light on the actual correlation among the acoustic parameters and the prominence phenomenon from an typological point of view, by examining data derived from some stress-accented languages. 1.

This paper presents work in progress on the automatic detection of prosodic prominence in continuous speech. Prosodic prominence involves two different phonetic features: pitch accents, connected with fundamental frequency (F0) movements and syllable overall energy, and stress, which exhibits a strong correlation with syllable nuclei duration and mid-to-high-frequency emphasis. By measuring these acoustic parameters it is possible to build an automatic system capable of correctly identifying prominent syllables with an agreement, with human-tagged data, comparable with the inter-human agreement reported in the literature. This system does not require any training phase, additional information or annotation, it is not tailored to a specific set of data and can be easily adapted to different languages.