Open Challenges in Synthetic Speech Detection
arXiv:2209.07180 · doi:10.1109/WIFS55849.2022.9975433
Abstract
In this paper the current status and open challenges of synthetic speech detection are addressed. The work comprises an initial analysis of available open datasets and of existing detection methods, a description of the requirements for new research datasets compliant with regulations and better representing real-case scenarios, and a discussion of the desired characteristics of future trustworthy detection methods in terms of both functional and non-functional requirements. Compared to other works, based on specific detection solutions or presenting single dataset of synthetic speeches, our paper is meant to orient future state-of-the-art research in the domain, to quickly lessen the current gap between synthesis and detection approaches.
References in corpus (8)
- WaveNet: A Generative Model for Raw Audio
- European Union regulations on algorithmic decision-making and a "right to explanation"
- Federated Learning with Non-IID Data
- Domain Adaptation for Statistical Classifiers
- HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis
- Training Speech Recognition Models with Federated Learning: A Quality/Cost Framework
- End-to-end spoofing detection with raw waveform CLDNNs
- WaveFake: A Data Set to Facilitate Audio Deepfake Detection