"Hello? Who Am I Talking to?" A Shallow CNN Approach for Human vs. Bot Speech Classification
Alessandro Lieto, Daniele Moro, Francesco Devoti, Claudia Parera, Vincenzo Lipari, Paolo Bestagini, Stefano Tubaro
Abstract
Automatic speech generation algorithms, enhanced by deep learning techniques, enable an increasingly seamless and immediate machine-to-human interaction. As a result, the latest generation of phone-calling bots sounds more convincingly human than previous generations. The application of this technology has a strong social impact in terms of privacy issues (e.g., in customer-care services), fraudulent actions (e.g., social hacking) and erosion of trust (e.g., generation of fake conversation). For these reasons, it is crucial to identify the nature of a speaker, as either a human or a bot. In this paper, we propose a speech classification algorithm based on Convolutional Neural Networks (CNNs), which enables the automatic classification of human vs non-human speakers from the analysis of short audio excerpts. We evaluate the effectiveness of the proposed solution by exploiting a real human speech database populated with audio recordings from various sources, and automatically generated speeches using state-of-the-art text-to-speech generators based on deep learning (e.g., Google WaveNet).
BibTeX
@inproceedings{icassp2019_hellowhoamitalki,
title = {"Hello? Who Am I Talking to?" A Shallow CNN Approach for Human vs. Bot Speech Classification},
author = {Alessandro Lieto and Daniele Moro and Francesco Devoti and Claudia Parera and Vincenzo Lipari and Paolo Bestagini and Stefano Tubaro},
booktitle = {ICASSP 2019},
year = {2019}
}