Abstract

This paper first reviews the advantages and disadvantages associated with both pre-coordination and post-coordination in classification. It then argues that we can have the advantages of both if we couple a post-coordinated (synthetic) approach to classification with a user interface that privileges the word order in search queries. Several other advantages of such an approach to classification and search are reviewed. It better captures the nature of a work (or object), addresses important issues with respect to social diversity, and facilitates user queries. It produces subject strings that resemble sentence fragments; this serves to clarify the meaning of terms within the subject string, and makes subject strings more comprehensible since humans typically think in sentences. These various benefits are then illustrated in the classification of works of music. It is shown that many important characteristics of works of music are best handled by such a system. These are generally poorly addressed, or not addressed at all, by existing approaches to the classification of music.

Abstract

The results of a project on news segmentation at Radio Nacional de España (RNE) carried out by the RTVE Technological Innovation and Media Management areas is presented. The aim of this project is to apply artificial intelligence to automatically transcribe and cut the news items that make up a radio news program. The main goals of this project are to increase the accessibility of the content and to allow its reusability on various platforms and social media. The project was planned in two phases, covering system configuration and service delivery. The minimum quality criteria required were defined in advance, both for automatic voice transcription and for news segmentation. For the speech-to-text process, the highest word error rate (WER) allowed was 10%, while the precision rate for the news segmentation was 85%. System performance in both transcription and segmentation was considered to be sufficient, although a higher degree of accuracy in news cutting is expected in the coming months. The results show that, despite using these quite mature technologies, adjustment and learning processes and human intervention are still necessary.