@inproceedings{93ea30403aca4d14b96ef910f3945940,
title = "N for Parameter: Efficient Multi-Scale Neural Audio Super Resolution with GAN",
abstract = "We introduce N-GAN, an end-to-end GAN architecture for neural audio super resolution that can accommodate multiple input sample rates. We refer to our approach as 'Wave-to-Wave' to distinguish it from the 'Wave-to-Spectrogram-to-Wave' and 'Wave-and-Spectrogram-to-Wave' approaches upon which the state-of-the-art results on this task are based. Our proposed 'Wave-to-Wave' architecture produces models that are orders of magnitude smaller than current state-of-the-art models whilst matching or exceeding their performance. In addition, our approach improves inference speed by at least 150\% (2.5x speedup) over previous similarly performant models. We show that our model obtains state-of-the-art performance on a target sample rate of 48kHz and input sample rates of 8kHz, 16kHz and 24kHz.",
author = "Mark Magumba and Steven Davy and \{Bin Zuber\}, Owais",
note = "Publisher Copyright: {\textcopyright} 2025 The Authors.; 28th European Conference on Artificial Intelligence, ECAI 2025, including 14th Conference on Prestigious Applications of Intelligent Systems, PAIS 2025 ; Conference date: 25-10-2025 Through 30-10-2025",
year = "2025",
month = oct,
day = "21",
doi = "10.3233/FAIA250821",
language = "English",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press BV",
pages = "313--321",
editor = "Ines Lynce and Nello Murano and Mauro Vallati and Serena Villata and Federico Chesani and Michela Milano and Andrea Omicini and Mehdi Dastani",
booktitle = "ECAI 2025 - 28th European Conference on Artificial Intelligence, including 14th Conference on Prestigious Applications of Intelligent Systems, PAIS 2025 - Proceedings",
address = "Netherlands",
}