Speech Content Authentication Research Articles

Strengthening speech content authentication against tampering

It is vital to authenticate the content of speech signals to prevent the framing of innocent individuals. Furthermore, lack of speech content authentication may lead to repudiation. The research problem of authenticity vs falsehood is timely considering the recent worldwide interest in fake news and viral manipulated media. Liu & Wang proposed an algorithm to detect tamperings in speech content, based on semi-fragile watermarking. These techniques embed a watermark imperceptibly in the speech signal. Semantic changes to the speech will destroy the watermark, while signal processing operations will not affect the watermark. One main criterion for these speech content authentication schemes is the ability to withstand tampering attacks. We present a cryptanalysis attack framework for watermark based media authentication schemes. To exemplify this, two media authentication schemes and corresponding attacks are modelled within this framework. We discuss the main reasons leading to the attacks and propose a strategy to strengthen the Liu & Wang algorithm against such attacks.

Multi-format speech BioHashing based on energy to zero ratio and improved LP-MMSE parameter fusion

In order to solve the problems of poor security and small application scope of speech content authentication, and to improve the robustness, discrimination and real-time performance of speech authentication, a multi-format speech BioHashing algorithm based on energy to zero ratio and improved linear prediction minimum mean square error (LP-MMSE) parameter fusion is proposed. Firstly, the algorithm extracts the short-term logarithmic energy, zero-crossing rate and the covariance method’s LP-MMSE of speech signal to be processed. Then, the time-frequency parameters are fused, and the fused feature vector and the orthogonal normalized random matrix of the key control are generated into BioHashing sequences through the inner product form. Finally, the BioHashing is encrypted by equal-length scrambling using henon chaotic map. The experimental results show that the proposed algorithm not only has the characteristics of good discrimination, strong robustness, good security, high real-time performance and wide application range, but also realizes the detection and localization of small-scale tampering of speech through minimum code distance (MCD) algorithm. At the same time, the algorithm also validates the unidirectionality of BioHashing with trapdoor by comparative difference method.

An efficient speech perceptual hashing authentication algorithm based on DWT and symmetric ternary string

According to the situation that speech perceptual hashing methods are not appropriated for real-time speech content authentication in mobile computing environment, a novel DWT-based perceptual hashing algorithm, which uses a combination of time-domain and frequency-domain features, was proposed to protect the speech data in the cloud. Firstly, by discrete wavelet transform (DWT), a new signal in frequency-domain is generated from the original speech signal after pre-processing and intensity-loudness transform (ILT). Secondly, coefficients of low frequency wavelet decomposition are partitioned into equal-sized and non-overlapping blocks, and logarithmic short-time energy of each block is computed to obtain speech signals features in frequency-domain. Finally, combined with spectral flux features (SFF) of speech signal in time-domain, a ternary perceptual hashing sequence is created. Experiment results illustrate that ternary form is better to stand for hash digest than binary form, the proposed algorithm has a good robustness against content preserving operations, discrimination, good compaction and high efficiency, and detects the tamper localisation as well.

Speech Content Authentication Scheme based on High-Capacity Watermark Embedding

The existed content authentication schemes based on digital watermark have some shortcomings. In order to solve the problems, a speech content authentication scheme based on high-capacity watermark embedding is proposed, and the high-capacity embedding method is discussed. Firstly, speech signal is framed and segmented, and the samples of each segment are scrambled. Secondly, DCT is performed on the scrambled signal, and low-frequency coefficients are selected as the watermark embedding domain. Lastly, frame number is mapped to a sequence of integers and embedded into the domain based on the embedding method. Theoretical analysis and experimental evaluation results show that the proposed algorithm is inaudible, robust to desynchronous attacks, enhances the embedding capacity, and improves the security of watermark system.

A speech content authentication algorithm based on a novel watermarking method

Some audio watermark schemes robust against desynchronization attacks are based on synchronization code embedded by quantifying signal energy, which have some shortcomings. Such as, (1) they do not verify the authenticity of watermarked signal detected. (2) They are vulnerable to substitution attack. To address the shortcomings and considering the background, a speech content authentication algorithm is proposed in this paper. Firstly, the original speech signal is framed, and each frame is cut into some segments. Secondly, samples of the segments are scrambled, and self-correlation of the scrambled signal is calculated. Lastly, watermark bit generated by frame number is embedded by quantifying the self-correlation. If watermarked signal is attacked, the attacked frames can be detected according to the frame number extracted. Theoretical analysis and experiments demonstrate that the scheme is robust against desynchronization attacks, improves the security, and has a good performance in ability of tampering location.

A Secure Speech Content Authentication Algorithm Based on Discrete Fractional Fourier Transform

Watermark schemes content-based provide one way to solve the veracity and integrity of speech content. Some existed content-based schemes are vulnerable to feature-analysed substitution attack. Aiming to solve the problems, a secure speech content authentication algorithm is proposed, on the basic of the undeterminate angle of discrete fractional fourier transform. In the paper, the definition and calculation of discrete fractional fourier transform are given. And the watermark generation method based on discrete fractional fourier transform is analyzed. Frame number and watermark bits are embedded into hybrid domain of scrambled signals. Compared with the existed watermark schemes, the features for watermark generation and embedding are secret, which improves the security of watermark system. Theoretical analysis and experimental evaluation results show that the proposed algorithm is inaudible, robust to desynchronous attacks and has the excellent ability of tamper detection and tamper location.

A Robust Speech Content Authentication Algorithm Against Desynchronization Attacks

A robust speech content authentication algorithm against desynchronization attacks is proposed, in order to authenticate the content of digital speech signal. Firstly, the signal is framed, and each frame is divided into two parts. The frame number of each frame, as the watermark bit, is embedded into the first and second part by quantizing Bessel-Fourier moments of the correspond signals. The content of each frame is authenticated by comparing with the watermark bits extracted from the first and second part. Experiment results shown that the authentication scheme against desynchronization attacks proposed is effective. And comparing with some existing schemes, the performance of scheme is improved. Index Terms—Speech watermarking, tamper detection, content authentication, bessel-fourier moments

A novel speech content authentication algorithm based on Bessel–Fourier moments

For audio watermark schemes, the method robust against desynchronization attacks based on synchronization codes faces security challenges. In this paper, a content-based method robust against insertion and deletion attacks is given, which is aimed to solve the insecurity problem of synchronization codes embedding, and a speech content authentication algorithm based on Bessel–Fourier moments is proposed. The definition and fast computation of Bessel–Fourier moments of discrete signal are given, and the attack on synchronization codes embedding method is described. For the scheme proposed, the non-synchronized signals caused by desynchronization attack can be re-synchronized by finding the frame that the watermark generated and extracted are equal. Comparing with the synchronization codes embedding method, the scheme not only is robust against insertion and deletion attacks, but also improves the security of watermark system. Theoretical analysis and experimental evaluation results show that the scheme is effective.

A Speech Content Authentication Algorithm Based on Pseudo-Zernike Moments in DCT Domain

A speech content authentication algorithm based on pseudo-Zernike moments in DCT domain is proposed in this paper, which is aimed at some shortcomings in some existing digital watermark schemes. The definition of coefficients self-correlation degree is given. Then the frequency domain watermark embedding method based on pseudo-Zernike moments in DCT domain is proposed. Watermark bits are generated by coefficients self-correlation degree and embedded by quantizing the pseudo-Zernike moments of DCT domain low-frequency coefficients. Comparing with the existing audio watermark algorithms based on pseudo-Zernike moments, the algorithm increases the watermarking embedding capacity and improves the efficiency greatly. Theoretical analysis and experimental evaluation results show that the proposed speech content authentication algorithm is effective.