This paper reports on a cooperative international evaluation of grapheme-to-phoneme (GP) conversion for text-to-speech synthesis in French. Test methodology and test corpora are described. The results for eight systems are provided and analysed in some detail. The contribution of this paper is twofold: on the one hand, it gives an accurate picture of the state-of-the-art in the domain of GP conversion for French, and points out the problems still to be solved. On the other hand, much room is devoted to a discussion of methodological issues for this task. We hope this could help future evaluations of similar systems in other languages.
Reading while listening to texts (RWL) is a promising way to improve the learning benefits provided by a reading experience. In an exploratory study, we investigated the effect of synchronizing the highlighting of words (visual) with their auditory (speech) counterpart during a RWL task. Forty French children from 3rd to 5th grade read short stories in their native language while hearing the story spoken by a narrator. In the non-synchronized (S-) condition the text was written in black on a white background, whereas in the synchronized (S+) RWL, the text was written in grey and the words were dynamically written in black when they were aurally displayed, in a karaoke-like fashion. The children were then unexpectedly tested on their memory for the orthographic form and semantic category of pseudowords that were included in the stories. The effect of synchronizing was null in the orthographic task and negative in the semantic task. Children's preference was mainly for the S-condition, except for the poorest readers who tended to prefer the S+ condition. In addition, the children's eye movements were recorded during reading. Gaze was affected by synchronization, with fewer but longer fixations on words, and fewer regressive saccades in the S+ condition compared to the S-condition. Thus, the S+ condition presumably captured the children's attention toward the currently heard word, which forced the children to be strictly aligned with the oral modality.
International audienceThe goal of this paper is to model the coverbal behavior of a subject involved in face-to-face social interactions. For this end, we present a multimodal behavioral model based on a Dynamic Bayesian Network (DBN). The model was inferred from multimodal data of interacting dyads in a specific scenario designed to foster mutual attention and multimodal deixis of objects and places in a collaborative task. The challenge for this behavioral model is to generate coverbal actions (gaze, hand gestures) for the subject given his verbal productions, the current phase of the interaction and the perceived actions of the partner. In our work, the structure of the DBN was learned from data, which revealed an interesting causality graph describing precisely how verbal and coverbal human behaviors are coordinated during the studied interactions. Using this structure, DBN exhibits better performances compared to classical baseline models such as Hidden Markov Models (HMMs) and Hidden Semi-Markov Models (HSMMs). We outperform the baseline in both measures of performance, i.e. interaction unit recognition and behavior generation. DBN also reproduces more faithfully the coordination patterns between modalities observed in ground truth compared to the baseline models
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.