POLIPHONE: A Dataset for Smartphone Model Identification from Audio Recordings

TL;DR

POLIPHONE, a dataset for smartphone model identification from audio recordings, includes data from 20 recent smartphones recorded in a controlled environment to ensure reproducibility and scalability for future research and presents numerous experiments to benchmark the proposed dataset using a state-of-the-art classifier.

Abstract

When dealing with multimedia data, source attribution is a key challenge from a forensic perspective. This task aims to determine how a given content was captured, providing valuable insights for various applications, including legal proceedings and integrity investigations. The source attribution problem has been addressed in different domains, from identifying the camera model used to capture specific photographs to detecting the synthetic speech generator or microphone model used to create or record given audio tracks. Recent advancements in this area rely heavily on machine learning and data-driven techniques, which often outperform traditional signal processing-based methods. However, a drawback of these systems is their need for large volumes of training data, which must reflect the latest technological trends to produce accurate and reliable predictions. This presents a significant challenge, as the rapid pace of technological progress makes it difficult to maintain datasets that are up-to-date with real-world conditions. For instance, in the task of smartphone model identification from audio recordings, the available datasets are often outdated or acquired inconsistently, making it difficult to develop solutions that are valid beyond a research environment. In this paper we present POLIPHONE, a dataset for smartphone model identification from audio recordings. It includes data from 20 recent smartphones recorded in a controlled environment to ensure reproducibility and scalability for future research. The released tracks contain audio data from various domains (i.e., speech, music, environmental sounds), making the corpus versatile and applicable to a wide range of use cases. We also present numerous experiments to benchmark the proposed dataset using a state-of-the-art classifier for smartphone model identification from audio recordings.

Figures (7)

• Figure 1: Recording setup used during the acquisition of the dataset tracks in the anechoic environment.
• Figure 2: Waveforms of the sine sweep signals recorded by all the considered smartphone models.
• Figure 3: Spectral representations of the Impulse Responses of all the considered smartphone models.
• Figure 4: Mel-spectrogram representations of the noisy speech signals recorded by all the considered smartphone models.
• Figure 5: Balanced accuracy values of the considered baseline, trained on different percentages of the training set.