Speech Audio Splicing Detection and Localization Exploiting Reverberation Cues

Abstract

Manipulating speech audio recordings through splicing is a task within everyone's reach. Indeed, it is very easy to collect through social media multiple audio recordings from well-known public figures (e.g., actors, politicians, etc.). These can be cut into smaller excerpts that can be concatenated in order to generate new audio content. As a fake speech from a famous person can be used for fake news spreading and negatively impact on the society, the ability of detecting whether a speech recording has been manipulated is a task of great interest in the forensics community. In this work, we focus on speech audio splicing detection and localization. We leverage the idea that distinct recordings may be acquired in different environments, which are typically characterized by distinctive reverberation cues. Exploiting this property, our method estimates inconsistencies in the reverberation time throughout a speech recording. If reverberation inconsistencies are detected, the audio track is tagged as manipulated and the splicing point time instant is estimated.

The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detection

“…Classic audio forgery detection algorithms usually perform classification by relying on hand crafted features such as Constant-Q Cepstral Coefficients [33], Log Magnitude Spectrum or phase-based features like Group Delay [34] and Linear Frequency Cepstral Coefficients (LFCC) or MFCCs [35]. More discriminative representations have been recently proposed by exploiting the bicoherence matrix [36], long-short term features computed in an autoregressive manner [37], environmental cues [6], and even emotions [7].…”

“…Some other strategies rely on the effects of the physical acquisition environment on the signal (e.g., reverberation, noise, etc.) [4]- [6] or on prosodic and emotional characteristics [7]. Other solutions rely on statistics and symmetry properties of speech signals [8].…”

Pyramid Feature Attention Network for Speech Resampling Detection

“…Contemporary speech forensics techniques are pivotal in ensuring the integrity of digital avatars and focus on detecting tampering facilitated by audio editing software, such as deletion, insertion, copy and move, splicing, resampling and recompression of audio clips [4][5][6][7]. It is worth noting that in the field of speech content forensics, there are more forensic methods for speech deletion, copy and move, splicing, and other tampering approaches [8][9][10], while there are relatively few methods for speech resampling forensics, and these tampering means are often accompanied by resampling operations. Thus, the study of speech resampling detection has significance in complex forensics environments, which will provide comprehensive tools and methods for forensics to ensure the authenticity and integrity of audio.…”

Detecção de edições em áudios baseada na análise tempo-frequência e em redes neurais convolucionais

“…Ao longo dos últimos anos, diversos métodos foram propostos para a detecção passiva de adulterações em registros de áudio, incluindo: verificação da continuidade de fase do sinal da rede elétrica (Electrical Network Frequency -ENF) [3][7], análise da variação espectral do padrão do rúido de fundo [11][10], estudo da correlação estatística nas dependências lineares dos pontos do sinal através da decomposição em valores singulares (Singular Value Decomposition -SVD) [12], análise de inconsistências no tempo de reverberação em uma gravação de áudio [2]. Esses métodos exigem, como etapa de pré-processamento, a extração manual do vetor de características (features).…”