The integration of Next Generation Audio (NGA) and Artificial Intelligence (AI) technologies is transforming the way narratives are developed in audiovisual productions, enabling increasingly immersive and interactive experiences.
As a result, it is necessary to reconsider narrative approaches and incorporate new technologies into production processes. Technological advances have unlocked the potential of non-linear user-driven narratives, but there is a need to expand access to production and development technologies, and implement regulations to improve distribution and access for independent producers.
It is crucial to raise the awareness of artists, content producers and users about the impact of the use and distribution of data on digital platforms for creative work, and pay attention to the representation of minorities in AI-generated data to ensure inclusive narratives and representative.
This research aims to comprehensively analyze the impact of NGA and AI on user experiences and reshape the digital storytelling landscape by compiling resources and tools for immersive productions.
Next Generation Audio (NGA) refers to the latest audio technologies and standards designed to give users a more immersive and personalized audio experience. NGA aims to improve the quality, flexibility and interactivity of audio content delivery, particularly in broadcast media.
NGA incorporates advanced technologies such as object-based audio, 3D audio, higher resolution in the field of audio spatialization.
Spatial audio creates a sense of space and placement, allowing for a more immersive and realistic audio experience by positioning and moving sounds in a virtual space. It is a key component of next-generation audio, which aims to create engaging and dynamic audio experiences through advances in sound quality, delivery methods, and interactive features. With the growth of technologies like virtual and augmented reality, the demand for spatial audio has increased significantly.
The use of artificial intelligence (AI) and machine learning in spatial audio can create personalized and immersive audio experiences. AI can enhance spatial audio by analyzing various factors such as the listener’s head position and movement, the acoustic properties of the listening environment, and the audio content.
AI can be used for object-based audio, where individual audio components like instruments or voices are divided into objects that can be positioned within the 3D sound field. AI algorithms can analyze the content of these objects and adjust their location and spatial level automatically to create a natural and immersive sound field. Room correction is another application of AI in spatial audio where algorithms can analyze the acoustic properties of a listening environment and make adjustments to compensate for distortions that can impact spatial audio perception.
