Application of Extractive Text Summarization Algorithms to Speech-to-text Media Domínguez M. Victor 4 , Fidalgo F. Eduardo 1,3 , Rubel Biswas 1,3 , Enrique Alegre 1,3 , Laura Fernández-Robles 2,3 1 Department of Electrical, Systems and Automatics Engineering, Universidad de León, Spain 2 Department of Mechanical, IT and Aerospatial Engineering, Universidad de León, Spain 3 Researcher at INCIBE (Spanish National Institute of Cybersecurity), Leon, Spain 4 Summer Research stay at GVIS Research Group vdomim00@estudiantes.unileon.es, {eduardo.fidalgo, rbis, enrique.alegre, l.fernandez}@unileon.es Abstract. This paper presents how speech-to-text summarization can be performed using extractive text summarization algorithms. Our objective is to make a recommendation about which of the six text summary algorithms evalu- ated in the study is the most suitable for the task of audio summarization. First, we have selected six text summarization algorithms: Luhn, TextRank, LexRank, LSA, SumBasic, and KLSum. Then, we have evaluated them on two datasets, DUC2001 and OWIDSum, with six ROUGE metrics. After that, we have se- lected five speech documents from ISCI Corpus dataset, and we have transcribed using the Automatic Speech Recognition (ASR) from Google Cloud Speech API. Finally, we applied the studied extractive summarization algorithms to these five text samples to obtain a text summary from the original audio file. Experimental results showed that Luhn and TextRank obtained the best performance for the task of extractive speech-to-text summarization on the samples evaluated. Keywords: Audio signal summarization, Speech-to-text summarization, Extrac- tive text summarization, Natural Language Processing. 1 Introduction Every day new platforms, services and applications emerge and manage a large amount of information, the vast majority in multimedia format, such as images, audio or video. Speech is one of the most effective methods of communication. However, it is not very easy to reuse, review or retrieve speech documents if they are contained on an audio signal. Extracting useful insights from an audio file is a hard task, especially if the number of audio files or their length is high. Besides, conversations from audio might include redundant information, e.g. word fragments, fillers or repetitions, to- gether with irrelevant information not related to the topic of interest or the objective followed. For these reasons, automatic summarization of audio files could help a user