Search

Speech quality is a critical consideration for applications such as speech enhancement, coding, transmission, and synthesis. Accurately evaluating the quality of degraded speech without a reference is particularly challenging. As a result, non-intrusive speech quality assessment has been extensively researched due to its efficiency and ease of deployment. This survey comprehensively reviews these studies. Commonly used speech quality assessment databases are reviewed, as they serve as validation sets for objective metrics. Non-intrusive speech quality assessment methods are categorized and reviewed, and the performance of state-of-the-art and classical speech quality assessment methods is compared. The survey presents an overview of classic algorithms and recent advancements in the field of non-intrusive speech quality assessment. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have been widely utilized as the main building block for many non-intrusive speech quality assessment (NISQA) methods. A new trend is to add a self-attention mechanism based on CNN to better capture long-term global content. However, it is not clear whether the pure attention-based network is sufficient to obtain good performance in NISQA. To this end, a framework named M ulti-dimension non-intrusive S peech Q uality A ssessment T ransformer (MSQAT) is proposed. To strengthen the interactions of various speech regions between local and global, we proposed the Audio Spectrogram Transformer Block (ASTB), Transposed Attention Block (TAB) and the Residual Swin Transformer Block (RSTB). These three modules employ attention mechanisms across spatial and channel dimensions, respectively. Additionally, speech quality varies not only in different frames, but also in different frequencies. Thus, a two-branch structure is designed to better evaluate the quality of speech by considering the weighting of each patch's score. Experimental results demonstrate that the proposed MSQAT has state-of-the-art performance on three standard datasets (NISQA Corpus, Tencent Corpus, and PSTN Corpus) and indicate that the pure attention model can achieve or surpass the performance of other CNN-attention hybrid models. • A pure attention-based model is proposed for NISQA tasks. • A two-branch architecture is proposed to score and weight different regions of speech. • The pure attention model can achieve or even surpass the performance of the hybrid attention model in experimental results. [ABSTRACT FROM AUTHOR]

Petitcolas has proposed a steganographic technique called MP3Stego which can hide secret messages in a MP3 audio. This technique is well-known because of its high capacity. However, in rare cases, the normal audio encoding process will be terminated due to the endless loop problem caused by embedding operation. In addition, the statistical undetectability of MP3Stego can be further improved. Inspired by MP3Stego, a new steganographic method for MP3 audio is proposed in this paper. The parity bit of quantization step rather than the parity bit of block size in MP3Stego is employed to embed secret messages. Compared with MP3Stego, the proposed method can avoid the endless loop problem and achieve better imperceptibility and higher security. [ABSTRACT FROM AUTHOR]

The number of channels is one of the important criteria in regard to digital audio quality. Generally, stereo audio with two channels can provide better perceptual quality than mono audio. To seek illegal commercial benefit, one might convert a mono audio system to stereo with fake quality. Identifying stereo-faking audio is a lesser-investigated audio forensic issue. In this paper, a stereo faking corpus is first presented, which is created using the Haas effect technique. Two identification algorithms for fake stereo audio are proposed. One is based on Mel-frequency cepstral coefficient features and support vector machines. The other is based on a specially designed five-layer convolutional neural network. The experimental results on two datasets with five different cut-off frequencies show that the proposed algorithm can effectively detect stereo-faking audio and has good robustness. [ABSTRACT FROM AUTHOR]

Convolutional neural networks can achieve remarkable performance in semantic segmentation tasks. However, such neural network approaches heavily rely on costly pixel-level annotation. Semi-supervised learning is a promising resolution to tackle this issue, but its performance still far falls behind the fully supervised counterpart. This work proposes a cross-teacher training framework with three modules that significantly improves traditional semi-supervised learning approaches. The core is a cross-teacher module, which could simultaneously reduce the coupling among peer networks and the error accumulation between teacher and student networks. In addition, we propose two complementary contrastive learning modules. The high-level module can transfer high-quality knowledge from labeled data to unlabeled ones and promote separation between classes in feature space. The low-level module can encourage low-quality features learning from the high-quality features among peer networks. In experiments, the cross-teacher module significantly improves the performance of traditional student–teacher approaches, and our framework outperforms state-of-the-art methods on benchmark datasets. [ABSTRACT FROM AUTHOR]

A multi-link network covert channel (MLCC) such as Cloak exhibits a high capacity and robustness and can achieve lossless modulation of the protocol data units. However, the mechanism of Cloak involving an arrangement of packets over the links (APL) is limited by its passive synchronization schemes, which results in intermittent obstructions in transmitting APL packets and anomalous link switching patterns. In this work, we propose a novel ordinal synchronization mark sequence (OSMS) for a Cloak framework based MLCC to ensure that the marked APL packets are orderly distinguishable. Specifically, a unidirectional function is used to generate the OSMS randomly before realizing covert modulation. Subsequently, we formulate the generation relation of the marks according to their order and embed each mark into the APL packets by using a one-way hash function such that the mark cannot be cracked during the transmission of the APL packet. Finally, we set up a retrieval function of the finite set at the covert receiver to extract the marks and determine their orders, and the APL packets are reorganized to realize covert demodulation. The results of experiments performed on real traffic indicated that the MLCC embedded with OSMS could avoid the passive synchronization schemes and exhibited superior performance in terms of reliability, throughput, and undetectability compared with the renowned Cloak method, especially under a malicious network interference scenario. Furthermore, our approach could effectively resist the inter-link correlation test, which are highly effective in testing the Cloak framework. [ABSTRACT FROM AUTHOR]

With the widespread availability of cell-phone recording devices, source cell-phone identification has become a hot topic in multimedia forensics. At present, the research on the source cell-phone identification in clean conditions has achieved good results, but that in noisy environments is not ideal. This paper proposes a novel source cell-phone identification system suitable for both clean and noisy environments using spectral distribution features of constant Q transform (CQT) domain and multi-scene training method. Based on the analysis, it is found that the identification difficulty lies in different models of cell-phones of the same brand, and their tiny differences are mainly in the middle and low frequency bands. Therefore, this paper extracts spectral distribution features from the CQT domain, which has a higher frequency resolution in the mid-low frequency. To evaluate the effectiveness of the proposed feature, four classification techniques of Support Vector Machine (SVM), Random Forest (RF), Convolutional Neural Network (CNN) and Recurrent Neuron Network-Long Short-Term Memory Neural Network (RNN-BLSTM) are used to identify the source recording device. Experimental results show that the features proposed in this paper have superior performance. Compared with Mel frequency cepstral coefficient (MFCC) and linear frequency cepstral coefficient (LFCC), it enhances the accuracy of cell-phones within the same brand, whether the speech to be tested comprises clean speech files or noisy speech files. In addition, the CNN classification effect is outstanding. In terms of models, the model is established by the multi-scene training method, which improves the distinguishing ability of the model in the noisy environment than single-scenario training method. The average accuracy rate in CNN for clean speech files on the CKC speech database (CKC-SD) and TIMIT Recaptured Database (TIMIT-RD) databases increased from 95.47% and 97.89% to 97.08% and 99.29%, respectively. For noisy speech files with seen noisy types and unseen noisy types, the performance was greatly improved, and most of the recognition rates exceeded 90%. Therefore, the source identification system in this paper is robust to noise. [ABSTRACT FROM AUTHOR]

Audio dual compression detection is an important part of audio forensics. It is of great significance to judge whether the audio has been falsified and forged. This study found that the advanced audio coding (AAC) audio scale factor gradually decreases with the number of compressions increases. Based on this, we propose an AAC double compression audio detection algorithm based on the statistical characteristics of the scale factor difference before and after audio re-compression. The experimental results show that the algorithm can accurately classify dual compressed AAC audio. The average accuracy of AAC audio classification between low-bit-rate transcoding to high-bit-rate is 99.91%, and the accuracy rate between the same bit rate is 97.98%. In addition, experiments with different durations, different noises, and different encoders also proved the better performance of this algorithm. [ABSTRACT FROM AUTHOR]