International audience

In spoken language, a significant proportion of words are produced with missing or underspecified segments, a phenomenon known as reduction. In this study, we distinguish two types of reductions in spontaneous speech: lexicalized reductions, which are well-documented, regularly occurring forms driven primarily by lexical processes, and non-lexicalized reductions, which occur irregularly and lack consistent patterns or representations. The latter are inherently more difficult to detect, and existing methods struggle to capture their full range. We introduce a novel bottom-up approach for detecting potential reductions in French conversational speech, complemented by a top-down method focused on detecting previously known reduced forms. Our bottom-up method targets sequences consisting of at least six phonemes produced within a 230ms window, identifying temporally condensed segments, indicative of reduction. Our findings reveal significant variability in reduction patterns across the corpus. Lexicalized reductions displayed relatively stable and consistent ratios, whereas non-lexicalized reductions varied substantially and were strongly influenced by speaker characteristics. Notably, gender had a significant effect on non-lexicalized reductions, with male speakers showing higher reduction ratios, while no such effect was observed for lexicalized reductions. The two reduction types were influenced differently by speaking time and articulation rate. A positive correlation between lexicalized and non-lexicalized reduction ratios suggested speaker-specific tendencies. Non-lexicalized reductions showed a higher prevalence of certain phonemes and word categories, whereas lexicalized reductions were more closely linked to morpho-syntactic roles. In a focused investigation of selected lexicalized items, we found that “tu sais” was more frequently reduced when functioning as a discourse marker than when used as a pronoun + verb construction. These results support the interpretation that lexicalized reductions are integrated into the mental lexicon, while non-lexicalized reductions are more context-dependent, further supporting the distinction between the two types of reductions.

This paper sheds light on a relatively unexplored area which is deep learning interpretability for speech disorder assessment and characterization. Building upon a state-of-the-art methodology for the explainability and interpretability of hidden representation inside a deep-learning speech model, we provide a deeper understanding and interpretation of the final intelligibility assessment of patients experiencing speech disorders due to Head and Neck Cancers (HNC). Promising results have been obtained regarding the prediction of speech intelligibility and severity of HNC patients while giving relevant interpretations of the final assessment both at the phonemes and phonetic feature levels. The potential of this approach becomes evident as clinicians can acquire more valuable insights for speech therapy. Indeed, this can help identify the specific linguistic units that affect intelligibility from an acoustic point of view and enable the development of tailored rehabilitation protocols to improve the patient’s ability to communicate effectively, and thus, the patient’s quality of life.

International audience

International audience

The popularity of Deep Neural Networks (DNNs) is growing significantly, and so is the interest in gaining a better understanding of their functioning. In this work, it is even more interesting to reveal the behavior of these black-boxes since we are involved in a clinical context. To this end, we propose a general analytic framework, namedNeuro-based Concept Detector (NCD), for interpreting deep representations of a DNN. Based on the activation patterns of the hidden neurons, this framework highlights the capacity of neurons to detect a specific concept related to the final task. The key strength of our framework is that it provides an interpretability tool for any type of DNN performing a classification task regardless of the application field. In this paper, we evaluate this framework on a Convolutional Neural Network (CNN) trained for the task of French phone classification. This choice was guided by the final objective of a long-term research project, which aims to identify the linguistic units best contributing to the maintenance or loss of intelligibility in the context of speech disorders. ThroughNCD, we demonstrate the emergence of phonetic features in the classification layers of the CNN-based model, while applied on healthy speech, a concept with a great interest in the field of clinical phonetics. Indeed, we further show that these interesting findings shed light on the characteristics of speech disorders in terms of altered phonetic features and provide relevant information for clinical practice, notably, patients' rehabilitation and follow-up.

Apart from the impressive performance it has achieved in several tasks, one of the most important factors remaining for the continuous progress of deep learning is the increased work related to interpretability, especially in a medical context. In a recent work, we presented competitive performance achieved with a CNN-based model trained on normal speech for the French phone classification and how it correlates well with different perceptual measures when exposed to disordered speech. This paper extends that work by focusing on interpretability. Here, the goal is to get insights into the way in which neural representations shape the final task of phone classification so that it can be used further to explain the loss of intelligibility in disordered speech. In this way, an original framework is proposed, relying firstly on the neural activity and a novel representation per neuron, here considering the phone classification, and, secondly, permitting to identify a set of neurons devoted to the detection of specific phonetic traits on normal speech. Faced to disordered speech, a degradation of that set of neurons is observed, demonstrating a loss of specific phonetic traits in some patients involved, and the potentiality of the proposed approaches to inform about speech alteration.

International audience

International audience

International audience

International audience

International audience

A comparison of how healthy and dysarthric pathological speakers adapt their production is a way to better understand the processes and constraints that interact during speech production in general. The present study focuses on spontaneous speech obtained with varying recording scenarios from five different groups of speakers. Patients suffering from motor speech disorder (dysarthria) affecting speech production are compared to healthy speakers. Three types of dysarthria have been explored: Parkinson's Disease, Amyotrophic Lateral Sclerosis and Cerebellar ataxia. This paper first presents general figures based on syllable-level annotation mining, including detailed information about healthy/pathological speakers variability. Then, we report on the results of automatic timing parsing of interval sequences in speech syllable annotations performed using TGA (Time Group Analysis) methodology. We observed that mean syllable-based speaking rates in time groups for the healthy speakers were higher than those measured in the recordings of dysarthric speakers. The variability in timing patterns (duration regression slopes, intercepts, and nPVI) depended also on the speaking styles in particular populations.

It is well known now that speech chain is not constituted by discrete units. Speech sounds have an influence on other sounds directly in contact with them. We hypothesize that this influence is not noise but plays an important role for perception. An experiment is managed to evaluate the relative importance of two kinds of cues: those of phonetic distinctive features (voiced and unvoiced) and those of voicing assimilation (for liquids). Our results confirm that voicing assimilation of liquids plays an important role to identifie clusters: a / the absence of assimilation cues increases reaction times; b/ subjects use assimilation cues in preference to distinctive features.

The claim that the syllable constitutes a basic perceptual unit in French is commonly accepted. It is based in part on the syllable effect [1] obtained with words. The present study extends these syllable detection experiments to pseudowords. Four experiments failed to replicate the syllable effect observed on words. Detection responses in pseudowords are made as soon as sufficient information becomes available in the signal. The different pattern of results obtained with words and pseudowords suggests that the syllable effect is post- lexical rather than pre-lexical.