"Hello? Who Am I Talking to?" A Shallow CNN Approach for Human vs. Bot Speech Classification

Lieto, Alessandro; Moro, Daniele; Devoti, Francesco; Parera, Claudia; Lipari, Vincenzo; Bestagini, Paolo; Tubaro, Stefano

doi:10.1109/icassp.2019.8682743

Cited by 23 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As an additional remark on the binary setup, it is worth noting that we also tested the purely data-driven method proposed in [8]. However, due to the heterogeneous nature of the used datasets, and the limited amount of available data when considering balanced classes, we could not achieve an accuracy higher than 0.72 on D dev and 0.71 on D eval .…”

Section: Binary Resultsmentioning

confidence: 99%

“…NNs have been proposed both for feature learning and classification steps. For example, in [8], a time frequency representation of the speech signal is presented at the input of a shallow CNN architecture. A similar framework is tested in [14].…”

Section: Fake Speech Detectionmentioning

confidence: 99%

“…Indeed, synthetic generation of both a video and an audio track opens the doors to new kinds of frauds, security breaches, and convincing fake news spreading methods. However, despite multiple forensic detectors have been proposed for video deepfake analysis [4][5][6][7], only a few techniques have been tailored to AI-generated speech analysis [8,9]. For this reason, in this paper we focus on synthetic audio speech detection.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Synthetic speech detection through short-term and long-term prediction traces

Borrelli

Bestagini

Antonacci

et al. 2021

EURASIP J. on Info. Security

View full text Add to dashboard Cite

Several methods for synthetic audio speech generation have been developed in the literature through the years. With the great technological advances brought by deep learning, many novel synthetic speech techniques achieving incredible realistic results have been recently proposed. As these methods generate convincing fake human voices, they can be used in a malicious way to negatively impact on today’s society (e.g., people impersonation, fake news spreading, opinion formation). For this reason, the ability of detecting whether a speech recording is synthetic or pristine is becoming an urgent necessity. In this work, we develop a synthetic speech detector. This takes as input an audio recording, extracts a series of hand-crafted features motivated by the speech-processing literature, and classify them in either closed-set or open-set. The proposed detector is validated on a publicly available dataset consisting of 17 synthetic speech generation algorithms ranging from old fashioned vocoders to modern deep learning solutions. Results show that the proposed method outperforms recently proposed detectors in the forensics literature.

show abstract

Section: Binary Resultsmentioning

confidence: 99%

Section: Fake Speech Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Synthetic speech detection through short-term and long-term prediction traces

Borrelli

Bestagini

Antonacci

et al. 2021

EURASIP J. on Info. Security

View full text Add to dashboard Cite

show abstract

“…Requires precise static calibration during enrollment/testing. Artifact Detection [16,17,32,52,54,91] Trains models to recognize spectral characteristics of synthetic speech.…”

Section: Defensementioning

confidence: 99%

"Hello, It's Me": Deep Learning-based Speech Synthesis Attacks in the Real World

Wenger

Bronckers

Cianfarani

et al. 2021

Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security

View full text Add to dashboard Cite

Advances in deep learning have introduced a new wave of voice synthesis tools, capable of producing audio that sounds as if spoken by a target speaker. If successful, such tools in the wrong hands will enable a range of powerful attacks against both humans and software systems (aka machines). This paper documents efforts and findings from a comprehensive experimental study on the impact of deep-learning based speech synthesis attacks on both human listeners and machines such as speaker recognition and voicesignin systems. We find that both humans and machines can be reliably fooled by synthetic speech, and that existing defenses against synthesized speech fall short. These findings highlight the need to raise awareness and develop new protections against synthetic speech for both humans and machines. CCS CONCEPTS• Computing methodologies → Machine learning; • Security and privacy → Biometrics.

show abstract

“…An important task within the NLP area is that of automated translation, which usually involves feature analysis (based on neural networks as well as Markov chains, for which software tools such as HTK or SPHINX are available [22]), unit detection (such as phonemes, [23]), syntactic analysis (for example, for word validation [24]), and proper translation via a looking-up procedure in a database. Remarkably, to the best of our knowledge, voice-to-voice translation by direct learning is not present in the literature with few exceptions for classification [25][26][27][28] and some others for translation: [2], which consists in a neural network composed by an 8-layer LSTM, an attention model for phonemes recognition and a voice synthesis module and [3] which uses a codebook of phonemes for translation with three stages, firstly there are some BiLSTM-layers to encoding the input data into phonemes, a convolutional middle layers and a final LSTM-layers for decoding the phonemes into an audio signal.…”

Section: Introductionmentioning

confidence: 99%

A Direct Speech-to-Speech Neural Network Methodology for Spanish-English Translation

Quintana¹,

Bernal²

2018

EAI Endorsed Transactions on Energy Web

View full text Add to dashboard Cite

In this work, a novel direct speech-to-speech methodology for translation is proposed; it is based on an LSTM neural network structure which has proven useful for translation in the classical way, i.e., the one consisting of three stages: speech-to-text conversion, text-to-text translation, and text-to-speech synthesis. In contrast with traditional approaches, the one in this work belongs to the recently appeared idea of direct translation without text representation, as this sort of training better corresponds to the way oral language learning takes place in humans. As a proof of concept digits are translated from an audio source in Spanish and pronounced as an audio signal in English. Advantages and disadvantages of the proposal when compared with traditional methodologies are discussed.

show abstract

"Hello? Who Am I Talking to?" A Shallow CNN Approach for Human vs. Bot Speech Classification

Cited by 23 publications

References 13 publications

Synthetic speech detection through short-term and long-term prediction traces

Synthetic speech detection through short-term and long-term prediction traces

"Hello, It's Me": Deep Learning-based Speech Synthesis Attacks in the Real World

A Direct Speech-to-Speech Neural Network Methodology for Spanish-English Translation

Contact Info

Product

Resources

About