3 resultados para Speech genre

em Repositório Científico do Instituto Politécnico de Lisboa - Portugal


Relevância:

20.00% 20.00%

Publicador:

Resumo:

In music genre classification, most approaches rely on statistical characteristics of low-level features computed on short audio frames. In these methods, it is implicitly considered that frames carry equally relevant information loads and that either individual frames, or distributions thereof, somehow capture the specificities of each genre. In this paper we study the representation space defined by short-term audio features with respect to class boundaries, and compare different processing techniques to partition this space. These partitions are evaluated in terms of accuracy on two genre classification tasks, with several types of classifiers. Experiments show that a randomized and unsupervised partition of the space, used in conjunction with a Markov Model classifier lead to accuracies comparable to the state of the art. We also show that unsupervised partitions of the space tend to create less hubs.

Relevância:

20.00% 20.00%

Publicador:

Resumo:

Cet article présente les premiers résultats d’une recherche s’intéressant à l’articulation entre imitation et invention dans l’écriture chez les jeunes scripteurs. L’étude s’attache à observer les modes de récupération de ressources textuelles fournies par les conditions de production. L’expérimentation a été conçue pour observer l’appropriation d’un genre. Des dispositifs didactiques ont été proposés à plusieurs classes de fin d’école primaire française, à partir de textes littéraires issus de la robinsonnade mis à disposition soit simultanément à l’acte d’écriture soit lors d’une seconde écriture. L’étude montre comment les élèves ont recours à deux procédés contrastés : le réinvestissement du lexique et la reformulation. Les données recueillies mettent en évidence la reprise attendue de mots caractéristiques du genre, et révèlent l’ingéniosité des scripteurs pour restructurer des matériaux langagiers. Certaines stratégies témoignent des difficultés rencontrées par les élèves qui ont eu à interpréter le lexique littéraire puis à le transférer dans leur propre récit. Des modes de reformulation différents coexistent dont on peut offrir une première catégorisation en fonction d’une appropriation plus ou moins réussie du genre considéré.

Relevância:

20.00% 20.00%

Publicador:

Resumo:

In research on Silent Speech Interfaces (SSI), different sources of information (modalities) have been combined, aiming at obtaining better performance than the individual modalities. However, when combining these modalities, the dimensionality of the feature space rapidly increases, yielding the well-known "curse of dimensionality". As a consequence, in order to extract useful information from this data, one has to resort to feature selection (FS) techniques to lower the dimensionality of the learning space. In this paper, we assess the impact of FS techniques for silent speech data, in a dataset with 4 non-invasive and promising modalities, namely: video, depth, ultrasonic Doppler sensing, and surface electromyography. We consider two supervised (mutual information and Fisher's ratio) and two unsupervised (meanmedian and arithmetic mean geometric mean) FS filters. The evaluation was made by assessing the classification accuracy (word recognition error) of three well-known classifiers (knearest neighbors, support vector machines, and dynamic time warping). The key results of this study show that both unsupervised and supervised FS techniques improve on the classification accuracy on both individual and combined modalities. For instance, on the video component, we attain relative performance gains of 36.2% in error rates. FS is also useful as pre-processing for feature fusion. Copyright © 2014 ISCA.