(Spanish) Identification of andean instruments using machine learning techniques

Andean Instrument Identification Using Machine Learning Techniques The identification of musical instruments from audio recordings is a complex task that represents a challenge for both human listeners and automated systems. This is because the sound produced by each instrument can vary considerably depending on factors such as the performer's technique, the instrument's condition, and the recording environment. Furthermore, when multiple instruments are played simultaneously, distinguishing between them becomes even more difficult. To address these challenges, we have sought to develop machine learning algorithms and deep neural networks capable of learning and classifying the different sounds of musical instruments with high accuracy. These models can be trained on large datasets of audio recordings, allowing them to capture the subtle acoustic differences that characterize each instrument [1].Beat tracking is a fundamental skill for any musician. According to an article published by Landr, rhythm in music is defined as the temporal organization of regular sound patterns [2]. Traditionally, Andean musicians have developed this skill by practicing with metronomes or following consistent rhythmic patterns. However, these techniques have significant limitations, as they do not offer effective real-time feedback or allow for efficient digital identification of rhythmic errors. In this context, the development of the proposed system emerges as an innovative response to the transformations that information technology has brought to music education. In the modern era, it is essential that educators adopt innovative pedagogical approaches and improved models that take advantage of available technological tools [3]. This application seeks to flexibly integrate computerized music technology to enrich the learning of traditional instruments from the Andean region. In doing so, it not only maximizes the potential of musicians but also promotes significant progress in music education, facilitating a more efficient, accessible, and personalized learning process.