{"type":"ScholarlyArticle","title":"Bridging the SEA Gap: An Initial Benchmark for Neural Audio Codec-Synthesized Speech Deepfakes in South-East Asian Languages","authors":[{"name":"Orchid Chetia Phukan","slug":"orchid-chetia-phukan","given":"Orchid","family":"Chetia Phukan","affiliation":""},{"name":"Girish","slug":"girish","given":"","family":"Girish","affiliation":""},{"name":"Mohd Mujtaba Akhtar","slug":"mohd-mujtaba-akhtar","given":"Mohd Mujtaba","family":"Akhtar","affiliation":""},{"name":"Arun Balaji Buduru","slug":"arun-balaji-buduru","given":"Arun Balaji","family":"Buduru","affiliation":""}],"abstract":"Codecfakes (CFs) are a type of speech deepfakes generated through Audio Language Models (ALMs), with Neural Audio Codecs (NACs) forming the core mechanism for speech encoding and generation. CFs exhibit distributional characteristics that differ from vocoder-based deepfakes, causing detectors trained on vocoder data to generalize poorly to CFs detection. Although this has led to the development of CF detection benchmarks, existing resources are largely confined to English—and to a limited extent Chinese—leaving South-East Asian (SEA) languages unexplored. To bridge this gap, we introduce SEA-CF, the first large-scale benchmark for CF detection spanning multiple SEA languages, diverse speaker profiles, and a wide range of NAC architectures. SEA-CF is constructed by synthesizing publicly available real speech corpora. Our experiments show that state-of-the-art (SOTA) CF detectors trained on English-centric datasets fail to generalize to SEA speech due to language-specific phonetic structures, tonal variations, and rich prosodic diversity. We further conduct a comprehensive zero-shot and fine-tuned evaluation of recent SOTA ALMs on SEA-CF. Fine-tuning the ALMs improves performance, however, these are very large being impractical for real-world application due to their scale, particularly in low-resource and latency-constrained settings. To address this limitation, we propose a novel small-ALM, GARUDA tailored for CF detection, which delivers strong performance while remaining lightweight. Extensive evaluations demonstrate that the proposed Small-ALM outperforms strong end-to-end and ALM-based baselines, establishing a new, practical direction for robust CF detection in SEA languages and beyond.","doi":"10.24963/ijcai.2026/791","url":"https://ijcai.org/proceedings/2026/791","pdf":"https://ijcai.org/proceedings/2026/0791.pdf","markdown":"https://ijcai.org/proceedings/2026/791.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/791","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI and Social Good","track":"AI and Social Good","number":791,"pages":{"first":7111,"last":7119},"keywords":["Natural Language Processing: Natural Language Processing","AI Ethics, Trust, Fairness: AI Ethics, Trust, Fairness"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}