National audienceHybrid techniques based both on symbolic (phonological) representations and probabilistic information are applied in modelling the form ~ function interface for the prosodic phenomena. The symbolic representation is acoustically oriented and agrees with the principles of intonational phonology. On the basis of this representation, two models of tonal segments sequences are calculated according to the paradigm of probabilistic grammars. We test both the bi-grams model end the patterns model and the models' performance is further evaluated with the entropy measure. Finally, the probabilistic models are tested in prediction.Nous explorons l'application des méthodes hybrides, reposant à la fois sur des représentations symboliqu...
The purpose of this paper is to define the framework within which empirical investigations of probab...
Proceedings of the Twenty-Sixth Annual Meeting of the Berkeley Linguistics Society: General Session ...
International audienceThe aim of this paper is to use Bayesian statistics to update a probability de...
National audienceHybrid techniques based both on symbolic (phonological) representations and probabi...
Nous explorons l’application des méthodes hybrides, reposant à la fois sur des représentations symbo...
International audienceMethodologically oriented, the present work sketches an approach for prosodic ...
International audienceThe present paper explores the issue of corpus prosodic parsing in terms of pr...
We present a probabilistic model of phonotactics, the set of well-formed phoneme sequences in a lang...
Speech prosody, the melodic and rhythmic properties of a language, plays a critical role in our ever...
Building models of language is a central task in natural language processing. Traditionally, languag...
Speech processing refers to a set of tasks that involve speech analysis and synthesis. Most speech p...
National audienceThe performance of many MIR analysis algorithms, most importantly polyphonic pitch ...
The notion of language as probabilistic is well known within Systemic Functional Linguistics. Aspect...
Linguistic typology studies the range of structures present in human language. The main goal of the ...
International audienceWe present a model to express preferences on rhythmic structure, based on prob...
The purpose of this paper is to define the framework within which empirical investigations of probab...
Proceedings of the Twenty-Sixth Annual Meeting of the Berkeley Linguistics Society: General Session ...
International audienceThe aim of this paper is to use Bayesian statistics to update a probability de...
National audienceHybrid techniques based both on symbolic (phonological) representations and probabi...
Nous explorons l’application des méthodes hybrides, reposant à la fois sur des représentations symbo...
International audienceMethodologically oriented, the present work sketches an approach for prosodic ...
International audienceThe present paper explores the issue of corpus prosodic parsing in terms of pr...
We present a probabilistic model of phonotactics, the set of well-formed phoneme sequences in a lang...
Speech prosody, the melodic and rhythmic properties of a language, plays a critical role in our ever...
Building models of language is a central task in natural language processing. Traditionally, languag...
Speech processing refers to a set of tasks that involve speech analysis and synthesis. Most speech p...
National audienceThe performance of many MIR analysis algorithms, most importantly polyphonic pitch ...
The notion of language as probabilistic is well known within Systemic Functional Linguistics. Aspect...
Linguistic typology studies the range of structures present in human language. The main goal of the ...
International audienceWe present a model to express preferences on rhythmic structure, based on prob...
The purpose of this paper is to define the framework within which empirical investigations of probab...
Proceedings of the Twenty-Sixth Annual Meeting of the Berkeley Linguistics Society: General Session ...
International audienceThe aim of this paper is to use Bayesian statistics to update a probability de...