This paper presents a semantic model which delivers personalized audio information. The personalization process is automated and decentralized. The metadata which support personalization are separated in two categorie...
详细信息
We present Open Review, a web-based platform aimed at stimulating executable papers by means of post-publication peer-review. Its goal is to bring computerscience researchers to collaboratively build their work upon ...
详细信息
We present Open Review, a web-based platform aimed at stimulating executable papers by means of post-publication peer-review. Its goal is to bring computerscience researchers to collaboratively build their work upon previous research results, in such a way that transparency, reproducibility and sustainability of research results are greatly improved. The main design goals of the platform are clarity, conciseness, and reproducibility. Its main features are to: (i) provide incentives for making research communities to participate, (ii) make papers executable by means of boards’ annotations, without necessarily involving the authors of an article, and (iii) give snapshots of the current research state on any given article.
This paper studies speech-driven Web retrieval models which accepts spoken search topics (queries) in the NTCIR-3 Web retrieval task. The major focus of this paper is on improving speech recognition accuracy of spoken...
详细信息
This paper studies speech-driven Web retrieval models which accepts spoken search topics (queries) in the NTCIR-3 Web retrieval task. The major focus of this paper is on improving speech recognition accuracy of spoken queries then improving retrieval accuracy in speech-driven Web retrieval. We experimentally evaluate the techniques of combining outputs of multiple LVCSR models in recognition of spoken queries. As model combination techniques, we compare the SVM learning technique conventional voting schemes such as ROVER. We show that the techniques of multiple LVCSR model combination can achieve improvement both in speech recognition and retrieval accuracies in speech-driven text retrieval. We also show that model combination by SVM learning outperforms conventional voting schemes both in speech recognition retrieval accuracies.
This paper describes a framework which provides health care professionals with a set of tools for building decision-theory based support systems for resource management optimization of health care policies in selected...
详细信息
暂无评论