# Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages

arXiv: https://arxiv.org/abs/2604.19949 · HTML: https://mlsanity.com/paper/2604.19949/

## Key facts

- Cited by 1 papers in the map (data through 20 Oct 2026).
- Placed in Anti-spoofing and adversarial audio attacks, one of 11 directions in Speech and audio language models.
- Builds on 33 of its 58 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Placed in

- Speech and audio language models / [Anti-spoofing and adversarial audio attacks](https://mlsanity.com/speech/anti-spoofing-and-adversarial-audio-attacks/)

## Builds on (most cited first, 30 of 33)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Moshi: a speech-text foundation model for real-time dialogue](https://mlsanity.com/paper/2410.00037/) (2024)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [Pengi: An Audio Language Model for Audio Tasks](https://mlsanity.com/paper/2305.11834/) (2023)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss](https://mlsanity.com/paper/1905.05879/) (2019)
- [Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities](https://mlsanity.com/paper/2503.03983/) (2025)
- [ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild](https://mlsanity.com/paper/2210.02437/) (2022)
- [AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec](https://mlsanity.com/paper/2305.16608/) (2023)
- [FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec](https://mlsanity.com/paper/2309.07405/) (2023)
- [MLAAD: The Multi-Language Audio Anti-Spoofing Dataset](https://mlsanity.com/paper/2401.09512/) (2024)
- [SNAC: Multi-Scale Neural Audio Codec](https://mlsanity.com/paper/2410.14411/) (2024)
- [IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages](https://mlsanity.com/paper/2208.11761/) (2022)
- [The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio](https://mlsanity.com/paper/2405.04880/) (2024)
- [StarGAN-VC2: Rethinking Conditional Methods for StarGAN-Based Voice Conversion](https://mlsanity.com/paper/1907.12279/) (2019)
- [Improved DeepFake Detection Using Whisper Features](https://mlsanity.com/paper/2306.01428/) (2023)
- [CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems](https://mlsanity.com/paper/2406.07237/) (2024)
- [ALLM4ADD: Unlocking the Capabilities of Audio Large Language Models for Audio Deepfake Detection](https://mlsanity.com/paper/2505.11079/) (2025)
- [Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake](https://mlsanity.com/paper/2404.00809/) (2024)
- [TRILLsson: Distilled Universal Paralinguistic Speech Representations](https://mlsanity.com/paper/2203.00236/) (2022)
- [SpeechFormer++: A Hierarchical Efficient Framework for Paralinguistic Speech Processing](https://mlsanity.com/paper/2302.14638/) (2023)
- [SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation Methods](https://mlsanity.com/paper/2507.21463/) (2025)
- [Codecfake: An Initial Dataset for Detecting LLM-based Deepfake Audio](https://mlsanity.com/paper/2406.08112/) (2024)
- [DFALLM: Achieving Generalizable Multitask Deepfake Detection by Optimizing Audio LLM Components](https://mlsanity.com/paper/2512.08403/) (2025)
- [End-to-end spoofing detection with raw waveform CLDNNs](https://mlsanity.com/paper/2007.13060/) (2020)
- [Curved Worlds, Clear Boundaries: Generalizing Speech Deepfake Detection using Hyperbolic and Spherical Geometry Spaces](https://mlsanity.com/paper/2511.10793/) (2025)

## Built on by (most cited first, 1 of 1)

- [Bridging the SEA Gap: An Initial Benchmark for Neural Audio Codec-Synthesized Speech Deepfakes in South-East Asian Languages](https://mlsanity.com/paper/2606.15968/) (2026)

## Abstract (arXiv)

The rapid advancement of Audio Large Language Models (ALMs), driven by Neural Audio Codecs (NACs), has led to the emergence of highly realistic speech deepfakes, commonly referred to as CodecFakes (CFs). Consequently, CF detection has attracted increasing attention from the research community. However, existing studies predominantly focus on English or Chinese, leaving the vulnerability of Indic languages largely unexplored. To bridge this gap, we introduce Indic-CodecFake (ICF) dataset, the first large-scale benchmark comprising real and NAC-synthesized speech across multiple Indic languages, diverse speaker profiles, and multiple NAC types. We use IndicSUPERB as the real speech corpus for generation of ICF dataset. Our experiments demonstrate that state-of-the-art (SOTA) CF detectors trained on English-centric datasets fail to generalize to ICF, underscoring the challenges posed by phonetic diversity and prosodic variability in Indic speech. Further, we present systematic evaluation of SOTA ALMs in a zero-shot setting on ICF dataset. We evaluate these ALMs as they have shown effectiveness for different speech tasks. However, our findings reveal that current ALMs exhibit consistently poor performance. To address this, we propose SATYAM, a novel hyperbolic ALM tailored for CF detection in Indic languages. SATYAM integrates semantic representations from Whisper and prosodic representations from TRILLsson using through Bhattacharya distance in hyperbolic space and subsequently performs the same alignment procedure between the fused speech representation and an input conditioning prompt. This dual-stage fusion framework enables SATYAM to effectively model hierarchical relationships both within speech (semantic-prosodic) and across modalities (speech-text). Extensive evaluations show that SATYAM consistently outperforms competitive end-to-end and ALM-based baselines on the ICF benchmark.