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.

Abstract

In recent decades, speech-based radio stations in Spain, whose programmes have been aimed at the general public, have transformed their on-demand content broadcasting strategy by incorporating audio processes in the form of podcasts, followed by transmission through websites, aggregators and applications. The overall objective of this article is to provide a detailed account of the evolution and scope of the podcast as an on-demand distribution channel for speech-based Spanish radio broadcasters, and to reveal how this format is changing the approaches taken by the most prominent national radio stations [Cadena SER, COPE, Onda Cero, and Radio Nacional de España (RNE)], with special emphasis on prime-time morning shows. The methodology employed combines quantitative and qualitative techniques along with an analysis of the content uploaded to the website of these morning programmes, which are part of the weekly programming cycle, together with semi-structured interviews using closed-ended questions that have been given to the main heads of programming and digital areas of the broadcasters under study. The results show that radio stations have incorporated podcast distribution into their usual routine in order to give new life to the content emitted, with the aim of serving both traditional users as well as new generations of digitised native listeners. In addition, they process daily content in an increasingly systematic way, on the basis of a model of mixed management coordination between programmes and digital areas. Similarly, broadcasters have made considerable progress in the measurement and analysis of the time-shifted audience, as well as in broadcast multiplication techniques using push notifications, social media, and monetisation.

Abstract

The radio broadcasting industry is facing a process of profound digital transformation throughout which, over the last 20 years, the strategies to preserve the traditional business model have prevailed. The consolidation of platformization and datafication in the economic management of the media requires adaptation of the radio broadcasting sector’s structures, management models, and corporate culture. Through an exhaustive bibliographic review, nonparticipant observation, and in-depth interviews conducted with heads of the systems, sales and marketing, content, and digital and innovation departments of the three leading Spanish companies (Prisa Radio, Grupo COPE, and Atresmedia Radio) and the state public broadcaster (RNE), we seek to identify the functional areas of the radio broadcasting company in which big data (BD) has a greater potential for application, trying to establish the differences in its utilization in the analogue and digital business model. The results revealed that the degree of BD implementation in the Spanish radio broadcasting industry was significantly different between the private sector –which within the last 2 or 3 years has begun to introduce, very incipiently, big data management, applied primarily to the analysis of digital audiences, these users’ consumer behavior, and business management– and the public sector, which so far has not adopted these technologies on a systematic basis.