Skip to content
Conference Open access

Multilingual Deepfake Audio Detection Using a Hybrid CNN-Bi LSTM with Multi-Head Attention Architecture

Aug 2026 · International Conference on Computing Communication Control and automation · pp. 1-11 · 0 citations · 16 references

TL;DR

This research proposes an approach towards deepfake audio detection across multiple languages, namely English, Hindi, and Marathi, with a novel approach, Hybrid CNN-BiLSTM with Multi-Head Attention Model, addressing the current shortcomings in the literature.

Abstract

Deepfake audio is a critical problem affecting information integrity, offering synthesized speech capable of fooling both humans and machines. This research proposes an approach towards deepfake audio detection across multiple languages, namely English, Hindi, and Marathi. It focuses on a novel approach, Hybrid CNN-BiLSTM with Multi-Head Attention Model, addressing the current shortcomings in the literature. Its model architecture consists of CNN layers to extract spatial features, BiLSTM layers to capture time dependency, and multi-head attention layers for context modeling, trained on Mel Frequency Cepstral Coefficients combined with delta and delta-delta coefficients. The dataset includes LibriSpeech for English language and OpenSLR for Indic languages with synthetic fakes created by augmentations like adding noise and changing the pitch. Robust preprocessing allows handling different lengths up to 120 seconds along with z-score normalization. The system is designed as a Flask web application, allowing users to record their voice and upload it, detect fake content, create a mimicry, and visualize spectrogram. The results show high accuracy (95.2%, 96.1% for English, 93.8% for Hindi, 92.5% for Marathi) with 4.8% equal error rate and high robustness against noise (85%+). Ablation study shows importance of each layer, filling research gaps in multilingual capabilities and hybrid model

Read PDF

Similar papers

#explainable ai Open access Oct 2026

Language-Conditioned Audio Adaptation for Multilingual Audio-Visual Deepfake Detection

Audio-visual deepfake detectors are increasingly deployed in multilingual settings, yet language-dependent speech variability can alter the behavior of audio branches trained without explicit language conditioning. This paper evaluates a MAVDD-style audio-visual detector on the French, Spanish, and Russian subsets of P...

Gurleen Kaur Sihra, Mohammad Abuzar Ansari · 0 citations
Sep 2026

DEVELOPMENT OF A MULTI-SCALE CONVOLUTIONAL ATTENTION ARCHITECTURE (MSCA-NET) FOR AUDIO DEEPFAKE DETECTION USING MEL-SPECTROGRAMS

Advancements in deepfake audio generation are increasingly endangering the reliability of speech biometrics, remote verification processes, and various digital messaging infrastructures. In this regard, the development of effective models that can detect synthetic speech with high accuracy is one of the current scienti...

A. Turarbek, Sh. Temirgaziyeva, A. S. Dokuz · 0 citations
Open access Sep 2026

Web-Integrated Deepfake Detection of Manipulated Political Audio Using CNN and Wav2Vec2 Transformer Models

Deepfake audio poses increasing risks to political forensics by enabling scalable misinformation, speaker impersonation, and identity spoofing. In response to this challenge, this paper presents a web-integrated deepfake detection framework for manipulated political speech together with a politically grounded multiling...

Patricio Mendoza Nuñez, Juan Pablo Astudillo León, Jefferson Alexander Moreno-Guaicha et al. · 0 citations
Open access 2026

Low-Resource Kichwa Mispronunciation Detection Using CNN and Wav2Vec2 Transformer-Based Deep Learning Models

Low-resource indigenous languages remain underrepresented in speech technologies, particularly in pronunciation assessment and computer-assisted language learning. This paper addresses automatic mispronunciation detection for Kichwa, an indigenous language spoken in Ecuador and other regions of Latin America. To suppor...

Saire Conejo, Juan Pablo Astudillo León, Sophia Cadoux et al. · 0 citations
Oct 2026

CDCLAP: Efficient distillation framework for zero-shot audio event classification.

This paper presents a novel Cross-Modal Distillation Contrastive Language-Audio Pretraining (CDCLAP) framework to address the challenges of zero-shot audio event classification (ZAEC) under limited hardware resources. The proposed method transfers visual knowledge from an ImageNet-pretrained MobileNetV3 to a lightweigh...

Fei Chen, Hui Xue, Peng-Fei Fang · 0 citations
Preprint Oct 2026

BabelFake: A Multilingual Audio-Visual DeepFake Benchmark

B BabelFake is introduced, a multilingual audio-visual DeepFake benchmark recorded with consenting participants, and it is shown that detection difficulty depends on the audio-visual generation pairing, with substantial performance degradation when authentic audio is preserved.

Carlotta Segna, Joel Tschesche, Anna Rohrbach · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.