Articles

________________________________________________________________________________________________________________ Development and implementation of fiduciary markers for vocal tract MRI i Development and implementation of fiduciary markers for vocal tract MRI i Development and implementation of fiduciary markers for vocal tract MRI i Development and implementation of fiduciary markers for vocal tract MRI imaging and speech maging and speech …...

Impact of the level of supervision on Web-based language model domain adaptation Domain adaptation of a language model aims at re-estimating word sequence probabilities in order to better match the peculiarities of a given broad topic of interest. To achieve this task, a common strategy consists in retrieving adaptation texts …...

________________________________________________________________________________________________________________ Mapping of the spectral space to the visual speech space for French vowels cued in Cued Speech In this paper, we present a statistical method based on GMM modeling to map the acoustic speech spectral features to visual features of Cued Speech in the sense of least square error …...

_______________________________________________________ Regional Variations of Speech Rhythm in French: In Search of Lost Times This paper addresses the relevance of speech rhythm acoustic measurements for the description of some standard, regional and contact varieties of French. First, the limitation of conventional speech rhythm measures (e.g. %V, ∆C or PVI) for the …...

Lexical-phonetic automata for spoken utterance indexing and retrieval This paper presents a method for indexing spoken utterances which combines lexical and phonetic hypotheses in a hybrid index built from automata. The retrieval is realised by a lexical-phonetic and semi-imperfect matching whose aim is to improve the recall. A feature vector, …...

_________________________________________________________________________________________________________ Reading and prosody in dyslexic children, pause patterns Dyslexia is widely associated with a deficit in phonological awareness. Only few works in suprasegmental phonology showed that prosody is involved in the processes of decoding and reading comprehension. We developed a corpus (DySpoLec) to examine various prosodic patterns in reading …...

_________________________________________________________________________________________________________ Acoustic characterization of phonologically voiced obstruents in Shanghai dialect In Shanghainese, phonologically voiced obstruents in word-initial, accented position are phonetically voiceless and are distinguished from the others (i.e., voiceless and/or aspirated) mainly by a low tone register. Slightly breathy voice is also reported in the relevant literature as an …...

Recognition of desynchronized consonantics sounds with and without fine spectral struc- ture This paper reports two experiments in which the identification of desynchronized VCV sequences was investigated with either both fine spectral structure (TFS) and envelope information or envelope information alone. These experiments compare the decrease in intelligibility scores with …...

_______________________________________________________________________________________________ Do you hear my attitudes? Do you hear my attitudes? Do you hear my attitudes? Do you hear my attitudes? PPPPerception of Mandarin Chinese social affects erception of Mandarin Chinese social affects erception of Mandarin Chinese social affects erception of Mandarin Chinese social affects’ prosody ’ prosody ’ prosody …...

__________________________________________________________________________________________________________ Prosodic Structuring and the Syntax-Prosody Relationship in Political Speech Studies on the prosodic structure of French recognize the existence of different types of prosodic constituents. These constituents differ from each other in the way in which they are constructed and realized. Generally speaking, prosodic structure is sensitive to syntactic …...

_________________________________________________________________________________________________________ Context and nature of phonetic realizations in conversational speech Since a decade, research in phonetics has turned with interest to the description of large corpora of casual speech. This new field of research opens up many opportunities but asks also new questions for phoneticians. Firstly, this paper evaluates the …...

_________________________________________________________________________________________________________ The prosodic structure of French involves a tight connection between the location of prominent syllables and locations where the flow of speech is divided into prosodic units. Researchers agree that the final (full) syllable of the smallest prosodic unit is prominent. The possibility remains that other syllables or words …...

French Liaison in casual speech : automatic and manual investigations The realisation of the French Liaison is investigated in a large corpus of casual speech. Consi- dering that casual speech gives rise to a large range of pronunciation variants and that overall temporal reduction increases (word and phone duration measurements) …...

Percol0 - A multimodal person detection system in video documents The goal of the PERCOL project is to participate to the REPERE multimodal evaluation program by building a consortium combining different scientific fields (audio, text and video) in order to perform person recognition in video documents. The two main scientific …...

_________________________________________________________________________________________________________ [lol]: a preliminary study of laughter in 18- to 36- month old children Laughter is a non-verbal vocal behavior that has been extensively studied in philosophy and biology, but researches investigating the phonetics of laughter are pretty rare. The aim of this study is to see whether there is …...

________________________________________________________________________________________________ Articulatory speaker normalisation based on MRI-data using three-way linear decomposition methods The aim of this study was to characterise, to model and to compare the different lingual articulatory strategies of a group of speakers. Individual principal component analysis (PCA) models and multi-linear decomposition methods have been applied to the …...

_______________________________________________________ Dialectal Effect on Articulation Rate in French This paper compares the articulation rate of 3 distinct varieties of French: Parisian French (hereafter PA); Swiss French spoken in Neuchâtel (hereafter NE) and French spoken by Swiss German speakers (hereafter CH) who have been living in a French speaking environment (in …...

________________________________________________________________________________________________________________________ Comparative study of the measurement accuracy of the 3D electromagnetic articulographs WAVE and AG500 We present a comparative study of the accuracy of the two most used 3D electromagnetic articulographs: NDI’s WAVE system and the Carstens AG500 system. To accurately judge their precision, we designed an experimental paradigm using …...

_________________________________________________________________________________________________________ Fine granularity scalable speech coding: Application to the G.729 coder This paper proposes an efficient codebook design for tree-structured vector quantization (TSVQ) which is embedded in nature. We modify the speech coding standard G.729 by replacing its original quantizer for line spectral frequencies (LSF’s) with TSVQ-based quantizer. The modified …...

REPERE : preliminary results of a multimodal person recognition challenge The REPERE Challenge aims at supporting researches on people recognition in multimodal conditions. To estimate the technology progress, annual evaluation campaigns on multimodal recognition of people in videos will be organized from 2012 to 2014. In this context, the REPERE …...