On reliability of log-spectral distortion measure in speech quality estimation

Prodeus, Arkadiy; Kotvytskyi, Igor

doi:10.1109/apuavd.2017.8308790

Cited by 7 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some parameters are tested to assess system capability in detecting, identifying, and retrieving attacked frames. These parameters are: a) Log spectrum distortion (LSD) measures the distortion in both watermarked and recovered signals [26]. b) Signal-to-noise ratio (SNR) [27].…”

Section: Resultsmentioning

confidence: 99%

An Efficient Tamper Detection and Recovery Scheme for Attacked Speech Signal

M. Jalil,

I. Shahadi,

R. Farhan

2024

IJCDS

View full text Add to dashboard Cite

Data security is an essential communication issue, where the resistivity to data tampering, corruption, and attacks forms a critical problem. This paper proposes a robust approach for tamper detection in a speech signal and recovering the destroyed parts of the attacked signal from the embedded spare parts using a specific strategy. The given approach deals with the abnormalities in the quality of the message speech signal that occurs due to different attacks. To solve that issue, A watermarking method is suggested to embed self-extracted data of authentication codes, synchronization identifiers, and spare part data from the same speech signal. The authentication codes are generated using the Singular Value Decomposition (SVD) method, while G.723.1 speech CODEC generates the spare part data. The proposed strategy considers attacks such as muting and replacement. According to the experiments, the quality of the watermarked and retrieved signals has improved. The average signal-to-noise ratio is above 70 dB for the watermarked signal quality, and the normalized correlation for the retrieved signal is close to the original speech signal under different operations. The results state fully recovering rate for the attacked signal under different types and lengths of attacks (10%-80% of Tampering Rates). Additionally, this approach achieves less distortion in the watermarked signal and the recovered signal quality measured by log spectrum distortion, which is about 0.0072 and 0.225 (at high Tampering Rate), respectively. The proposed approach is compared to the related methods, where it achieves the best results, including high robustness against different types of attacks.

show abstract

Section: Resultsmentioning

confidence: 99%

An Efficient Tamper Detection and Recovery Scheme for Attacked Speech Signal

M. Jalil,

I. Shahadi,

R. Farhan

2024

IJCDS

View full text Add to dashboard Cite

show abstract

“…1b with c, d, e, and f, it is obvious that the stationary white noise became highly non-stationary after the processing of DNNs, so that this kind of noise is referred to as artificial noise. Herein, a log-spectral distortion (LSD) measurement was conducted to test the speech quality degradation, where the LSD was calculated as [43] To further analyze and validate that the residual noise of the aforementioned DNNs is disturbing to a human listener, a psychoacoustic model was introduced to calculate the noise masking threshold of the enhanced speech signals. By taking consideration of the frequency selectivity and the masking property of the human ear, the noise masking threshold was calculated as in [18].…”

Section: Results and Analysismentioning

confidence: 99%

Low-complexity artificial noise suppression methods for deep learning-based speech enhancement algorithms

Zheng

et al. 2021

J AUDIO SPEECH MUSIC PROC.

View full text Add to dashboard Cite

Deep learning-based speech enhancement algorithms have shown their powerful ability in removing both stationary and non-stationary noise components from noisy speech observations. But they often introduce artificial residual noise, especially when the training target does not contain the phase information, e.g., ideal ratio mask, or the clean speech magnitude and its variations. It is well-known that once the power of the residual noise components exceeds the noise masking threshold of the human auditory system, the perceptual speech quality may degrade. One intuitive way is to further suppress the residual noise components by a postprocessing scheme. However, the highly non-stationary nature of this kind of residual noise makes the noise power spectral density (PSD) estimation a challenging problem. To solve this problem, the paper proposes three strategies to estimate the noise PSD frame by frame, and then the residual noise can be removed effectively by applying a gain function based on the decision-directed approach. The objective measurement results show that the proposed postfiltering strategies outperform the conventional postfilter in terms of segmental signal-to-noise ratio (SNR) as well as speech quality improvement. Moreover, the AB subjective listening test shows that the preference percentages of the proposed strategies are over 60%.

show abstract

“…x o x − x o quantifies the ratio between the energy of the target signal denoted by x o and residual error with an estimate x. In order to complement this signal-domain evaluation by a TF-domain quality measure [43], [44], we compute the Itakura-Saito (IS) divergence [45] using the discrete Fourier transform F of the signals, as…”

Section: Numerical Experimentsmentioning

confidence: 99%

Time-Frequency Fading Algorithms Based on Gabor Multipliers

Kreme

Emiya

Chaux

et al. 2021

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

In this paper, we address a particular instance of time-frequency filter design, which we call Time-Frequency Fading (TFF). In TFF the only available information concerns the time-frequency localization of the component to be filtered out or attenuated: the signal of interest is supposed to be spread out in the time-frequency plane, whereas the perturbation signal is concentrated within a specified time-frequency region Ω.The problem is formulated as an optimization problem designed to fade out the perturbation with accurate control on the fading level. The corresponding objective function involves a data fidelity term that aims to match the TF coefficients of the estimated signal to those of the observed signal outside the perturbation support. It also involves a penalty term that controls the energy of the reconstructed signal, within that region.We obtain the closed-form solution of the problem which involves Gabor multipliers, i.e. linear operators of the pointwise product by a time-frequency transfer function called a mask. We study the TF localization properties of dominant eigenvectors of these Gabor multipliers, with particular attention to the case where the region Ω is a disjoint union of several sub-regions. The decay properties of eigenvalues naturally lead to reducedrank approximations, and further approximations are obtained in the multiply connected region case. Also, we exploit random projection methods to speed up eigenvalue decompositions and rank reduction. This is implemented in two TFF algorithms, that cover the cases of single or multiple regions.The efficiency of the proposed approach is demonstrated on several audio signals where the perturbations are filtered while leading to a good quality of signal reconstruction.

show abstract

On reliability of log-spectral distortion measure in speech quality estimation

Cited by 7 publications

References 10 publications

An Efficient Tamper Detection and Recovery Scheme for Attacked Speech Signal

An Efficient Tamper Detection and Recovery Scheme for Attacked Speech Signal

Low-complexity artificial noise suppression methods for deep learning-based speech enhancement algorithms

Time-Frequency Fading Algorithms Based on Gabor Multipliers

Contact Info

Product

Resources

About