Using Deep Learning Techniques And Inferential Speech Statistics For AI Synthesised Speech Recognition

Abstract

The recent developments in technology have re-warded us with amazing audio synthesis models like TACOTRON and WAVENETS. On the other side, it poses greater threats such as speech clones and deep fakes, that may go undetected. To tackle these alarming situations, there is an urgent need to propose models that can help discriminate a synthesized speech from an actual human speech and also identify the source of such a synthesis. Here, we propose a model based on Convolutional Neural Network (CNN) and Bidirectional Recurrent Neural Network (BiRNN) that helps to achieve both the aforementioned objectives. The temporal dependencies present in AI synthesized speech are exploited using Bidirectional RNN and CNN. The model outperforms the state-of-the-art approaches by classifying the AI synthesized audio from real human speech with an error rate of 1.9% and detecting the underlying architecture with an accuracy of 97%.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysingh2021using

Related papers

• Deep Residual Neural Networks For Audio Spoofing Detection (2019)0.00
• Syn-att: Synthetic Speech Attribution Via Semi-supervised Unknown Multi-class Ensemble Of Cnns (2023)0.00
• Detection Of Ai-synthesized Speech Using Cepstral & Bispectral Statistics (2020)0.00
• Adaptive Re-calibration Of Channel-wise Features For Adversarial Audio Classification (2022)0.00
• Efficiently Trainable Text-to-speech System Based On Deep Convolutional Networks With Guided Attention (2017)16.41
• Light Convolutional Neural Network With Feature Genuinization For Detection Of Synthetic Speech Attacks (2020)13.97
• Fast And High-quality Singing Voice Synthesis System Based On Convolutional Neural Networks (2019)8.82
• Multi-modal Hybrid Deep Neural Network For Speech Enhancement (2016)0.00