Digital watermarking and tamper detection in speech signal using blind detection

Objective metrics, such as the perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI), and signal-to-distortion ratio (SDR), are often used for evaluating speech. These metrics are intrusive since they require a reference (clean) speech signal to complete the evaluation. The need for a reference signal reduces the practicality of these metrics, since a clean reference signal is not typically available during real-world testing. In this paper, a two-stage approach is presented that estimates the objective score of these intrusive metrics in a non-intrusive manner, which enables testing in real-world environments. More specifically, objective score estimation is treated as a machine-learning problem, and the use of speech-enhancement residuals and convolutional long short-term memory (SER-CL) networks is proposed to blindly estimate the objective scores (i.e., PESQ, STOI, and SDR) of various speech signals. The approach is evaluated in simulated and real environments that contain different combinations of noise and reverberation. The results reveal that the proposed approach is a reasonable alternative for evaluating speech, where it performs well in terms of accuracy and correlation. The proposed approach also outperforms comparison approaches in several environments.

Speech enhancement is of paramount importance in improving the intelligibility and audibility of speech signals in an uncontrolled noisy environment over wireless communication systems. However, the existing techniques used to achieve this such as spectral subtraction are characterized by remnant noise or musical note, while Kalman filter which can remove the remnant noise is associated with instability and non-linear characteristics. Therefore, this paper proposes speech enhancement model in noisy environment using hybrid spectral-Kalman filter over wireless communication system. The proposed model was carried out using acquired noisy speech signals by the Samsung Android mobile phone. The phone call was made in an uncontrolled noisy environment. The signal received was processed by the hybrid spectral-Kalman filter which was achieved by using the output speech signal from the spectral subtraction in time domain as the input of the Kalman filter. The proposed hybrid spectral-Kalman filtering technique was evaluated using Signal-to-Noise Ratio (SNR), Mean Square Error (MSE), Perceptual Evaluation of Speech Quality (PESQ) and Short-Time Objective Intelligibility (STOI). Comparison was then performed with the existing techniques and validation was performed using corrupted speech signals obtained from the NOIZEUS corpus data set. The result revealed that the proposed technique performed better than the existing techniques in a noisy environment.

The speech enhancement effect of traditional deep learning algorithms is not ideal under low signal-to-noise ratios (SNR). Skip connections-deep neural network (Skip-DNN) improves the traditional deep neural network (DNN) by adding skip connections between each layer of the neural network to solve the degradation problem of DNN. In this paper, the Multiresolution Cochleagram (MRCG) features in the gammachirp transform domain are denoised to obtain the improved MRCG (I-MRCG). The noise reduction method adopts the Minimum Mean-Square Error Short-Time Spectral Amplitude Estimator (MMSE-STSA) and takes I-MRCG as the input feature and Skip-DNN as the training network to improve the speech enhancement effect of the model. This paper also proposes an improved source-to-distortion ratio (SDR) loss function. When the loss function uses the improved SDR, it will improve the performance of Skip-DNN speech enhancement model. The experiments in this paper are performed on the Edinburgh dataset. When using I-MRCG as the input feature of Skip-DNN, the average perceptual evaluation of speech quality (PESQ) is 2.9137, and the average short-time objective intelligibility (STOI) is 0.8515. Compared with MRCG as Skip-DNN input features, the improvements are 0.91% and 0.71%, respectively. When the improved SDR is used as the loss function of the speech model, the average PESQ is 2.9699 and the average STOI is 0.8547. Compared with other loss functions, the improved SDR has a better enhancement effect when used as the loss function of the speech enhancement model.

Speech enhancement techniques are broadly classified into far-end, and near-end approaches. Unlike far-end speech enhancement techniques, the near-end speech enhancement approaches have access to both clean speech and noise for processing. The current work focusses on near-end listening enhancement, and aims to prevent the speech signal delivered in a noisy environment from losing its comprehensibility. The proposed work combines, proposed speech histogram matching based energy redistribution followed by Wiener filter based post processing. Particle swarm optimization (PSO) is applied during histogram matching in order to maintain the total energy in the matched signal with respect to the energy of the noisy speech signal. The proposed algorithm provides intelligibility improvement especially in the weak speech regions (i.e. consonants such as fricatives, stops, etc.,). The performance of the proposed algorithm is evaluated for a stationary noise condition at 0 dB and 5 dB noise levels, in terms of quality and intelligibility using perceptual evaluation of speech quality (PESQ), and coherence speech intelligibility index (CSII) and short time objective intelligibility (STOI) measures respectively. The algorithm is evaluated for a stationary noise condition. The results indicate that the proposed technique achieves greater intelligibility with no decrement in quality.

Noise suppression in speech signal has received great attention in signal processing research community. However, existing methods of noise suppression such as the time-domain Kalman filter suffers from the psychoacoustic and physiological characteristic feature while the spectral subtraction technique performed in the modulation domain is associated with remnant noise in the enhanced speech signal. Therefore, in this paper, a Modulation-Domain coupled Kalman-Spectral Filtering (MD-KSF) in a single channel system is proposed to address the aforementioned shortcomings in the two existing techniques. The simulation of the proposed coupled MD-KSF was performed in MATLAB software environment. The evaluation of the proposed coupled MD-KSF technique in terms of Spectral waveform, Mean Square Error (MSE) and Log Spectral Distance (LSD) was performed. Furthermore, Perceptual Evaluation of Speech Quality (PESQ) and Short-Time Objective Intelligibility (STOI) tests were employed to validate the quality and intelligibility of the proposed coupled MD- KSF using the NOIZEUS corpus data set. The proposed technique shows significant noise suppression over the existing techniques.

Speech signals are complex in nature with respect to other forms of communication media such as text or image. Different forms of noises (e.g., additive noise, channel noise, babble noise) interfere with the speech signals and drastically hamper the quality of the speech in the noisy speech signals. Enhancement of speech signals is a daunting task considering multiple forms of noises while denoising speech signals. Certain analog noise eliminator models have been studied over the years for this purpose. Researchers have also delved into some deep learning techniques to enhance speech signals. In this study, a speech enhancement system is investigated using Convolutional Denoising Autoencoder (CDAE). It takes advantages from the 2D structured inputs of the features extracted from speech signals and also considers the local temporal relationship among the features. In the proposed system, CDAE is trained considering features from noisy speech signal as input and clean speech features as desired output. The proposed CDAE based method has been tested on a benchmark dataset, called Speech Command Dataset, and attained 80% similarity between denoised speech and actual clean speech. The proposed system achieved perceptual evaluation of speech quality (PESQ) value of 2.43 which outperformed other related existing methods.

This study presents a Learning-based Tunable GlObal Audio Telepresence (LT-GOAT) system to bring the near end users to the virtual far end, with a tunable balance between the target source field and the ambient field consisting of interference and late reverberation for acoustic array systems. The system can seamlessly vary between “Enhanced” mode for speech quality and “Immersive” mode for spatial ambience. The far-end audio signals are captured by a microphone array, and then a neural network is pre-trained to separate the target source field and ambient sound. Another network is then implemented to perform multichannel filtering based on the model matching principle. The training process minimizes the matching error between the synthesized sound field and the desired sound field at the control points situated virtually at the far end. Simulations were conducted for the LT-GOAT system involving a four-microphone array at the far end and a six-loudspeaker array in the near end. A target source and an interferer at the far end were studied under various reverberation conditions. Performance was assessed using objective metrics including Perceptual Evaluation of Speech Quality (PESQ), Short-Time Objective Intelligibility (STOI) and matching errors. The results showed that the proposed system outperformed conventional baselines.

Although copy-move forgery is one of the most common fabrication techniques, blind detection of such tampering in digital audio is mostly unexplored. Unlike active techniques, blind forgery detection is challenging, because it does not embed a watermark or signature in an audio that is unknown in most of the real-life scenarios. Therefore, forgery localization becomes more challenging, especially when using blind methods. In this paper, we propose a novel method for blind detection and localization of copy-move forgery. One of the most crucial steps in the proposed method is a voice activity detection (VAD) module for investigating audio recordings to detect and localize the forgery. The VAD module is equally vital for the development of the copy-move forgery database, wherein audio samples are generated by using the recordings of various types of microphones. We employ a chaotic theory to copy and move the text in generated forged recordings to ensure forgery localization at any place in a recording. The VAD module is responsible for the extraction of words in a forged audio, and these words are analyzed by applying a 1-D local binary pattern operator. This operator provides the patterns of extracted words in the form of histograms. The forged parts (copy and move text) have similar histograms. An accuracy of 96.59% is achieved, and the proposed method is deemed robust against noise.

In this work, we propose a new strategy for deep mixture of experts (DMoE) based speech enhancement. DMoE system is difficult to train due to the specific network structure and the necessity of carefully designed pre-training methods to guarantee good performance. We propose using distinguishing deep neural networks (DNNs) as experts, dealing with magnitude spectrogram and log-magnitude spectrogram respectively. The proposed method is compared with the state-of-art DMoE system utilizing hard expectation maximization (HEM) pre-training method. Speech enhancement experiments in 30 (5*6) noise and SNR conditions show the superiority of the proposed method over the baseline method. The average improvements obtained for matched conditions are 0.076 in perceptual evaluation of speech quality (PESQ), 1.824dB in segmental signal to noise ratio (segSNR) and 0.043 in short time objective intelligibility (STOI).

Deep neural network(DNN)-based ideal ratio mask(IRM) estimation methods are often adopted in speech enhancement tasks. In the previous work, IRM estimation was usually realized by a single DNN-based IRM estimator without considering the SNR levels, which had a limited performance in real applications. Therefore, a two stage speech enhancement method is proposed in this paper. Firstly, a DNN-based SNR classifier is employed to classify the speech frames into three classes according to different SNR thresholds. Secondly, three corresponding DNN based IRM estimators related to the three SNR classes are trained respectively, from which the amplitude spectrum is corrected. Finally, speech enhancement is realized by doing IDFT to the corrected speech spectrum combined with the phase information of noisy speech. Experiment results show that the algorithm proposed in this paper has better performances in the evaluation of short time objective intelligibility(STOI), perceptual evaluation of speech quality(PESQ) and segmental signal-to-noise ratio improvement(SSNRI) scores.

Recent work in the domain of speech enhancement has explored the use of self-supervised speech representations to aid in the training of neural speech enhancement models. However, much of this work focuses on using the deepest or final outputs of self supervised speech representation models, rather than the earlier feature encodings. The use of self supervised representations in such a way is often not fully motivated. In this work it is shown that the distance between the feature encodings of clean and noisy speech correlate strongly with psychoacoustically motivated measures of speech quality and intelligibility, as well as with human Mean Opinion Score (MOS) ratings. Experiments using this distance as a loss function are performed and improved performance over the use of STFT spectrogram distance based loss as well as other common loss functions from speech enhancement literature is demonstrated using objective measures such as perceptual evaluation of speech quality (PESQ) and short-time objective intelligibility (STOI).

Speech communicated is adversely affected by environmental noise. It is important to process the speech and reduce noise for better understanding. Speech enhancement or noise reduction is useful to provide comfort for human or machine listening. Traditional algorithms provide better noise reduction and better-quality speech. Due to the non-stationary nature of noise and the quasi-stationary nature of speech, the traditional methods are proven inadequate in achieving high-quality speech. Later statistical estimators based on Gaussian, and super-Gaussian Probability Density Function (PDF) assumption further improved the enhancement performance. But still, non-stationary noise nature introduces artifacts in processed signal and results in decreased performance. It is observed that neural network approaches and the factorization approach provide better performance even under non-stationary noises by proper training and large database. Different features result in variations in output performance under unseen noise and speaker conditions. It is important to understand the importance and advantages of traditional methods, statistical estimators, and neural network approaches performances. To select the suitable method for a required application, it is essential to consider the trade-off between quality and distortion. In this work, the importance of speech enhancement methods is discussed. Performance measures used for understanding the speech enhancement like Signal to Noise Ratio (SNR), Segmental SNR, Log-Likelihood Ratio (LLR), Weighted Spectral Slope (WSS), Perceptual Evaluation of Speech Quality (PESQ), Short-Time Objective Intelligibility (STOI), Signal to Distortion Ratio (SDR) and Mean Opinion Score (MOS), are given. Highlights of important results are discussed for analyzing better speech enhancement methods for the required application. In this work, performance is compared using objective and subjective performance measures. Simulation results show superior performance when neural network is employed in statistical estimators.

Deep Neural Networks (DNNs) have been successfully adopted as a regression model in speech enhancement. However, the performance in the battlefield environment is not always satisfactory because the noise energy is often dominating in certain speech segments causing speech distortion. For the speech enhancement in complicated battlefield environment where multiple noises can simultaneously corrupt speech, such as gunshots and explosions, we propose an enhanced method to improve the existing DNN-based speech enhancement by using Recurrent Neural Networks (RNNs). This RNN model judges whether each frame is in a low SNR state, and then fuses two DNN-based speech enhancement models. The proposed method is compared with existing DNN-based speech enhancement techniques through the perceptual evaluation of speech quality (PESQ) and the short-time objective intelligibility (STOI) scores in various noisy speech conditions. The experimental results demonstrate significant improvements over the state-of-the-art techniques and reflect the usability of the method in a real battlefield environment.KeywordsSpeech enhancementDeep Neural Networks (DNNs)Recurrent Neural Networks (RNNs)Battlefield environment

In this paper, we considered the problem of the speech enhancement similar to the real-world environments where several complex noise sources simultaneously degrade the quality and intelligibility of a target speech. The existing literature on the speech enhancement principally focuses on the presence of one noise source in mixture signals. However, in real-world situations, we generally face and attempt to improve the quality and intelligibility of speech where various complex stationary and nonstationary noise sources are simultaneously mixed with the target speech. Here, we have used deep learning for speech enhancement in complex-noisy environments and used ideal binary mask (IBM) as a binary classification function by using deep neural networks (DNNs). IBM is used as a target function during training and the trained DNNs are used to estimate IBM during enhancement stage. The estimated target function is then applied to the complex-noisy mixtures to obtain the target speech. The mean square error (MSE) is used as an objective cost function at various epochs. The experimental results at different input signal-to-noise ratio (SNR) showed that DNN-based complex-noisy speech enhancement outperformed the competing methods in terms of speech quality by using perceptual evaluation of speech quality (PESQ), segmental signal-to-noise ratio (SNRSeg), log-likelihood ratio (LLR), weighted spectral slope (WSS). Moreover, short-time objective intelligibility (STOI) reinforced the better speech intelligibility.

This study proposes a bi-directional recurrent neural network (Bi-RNN) post-processing method for speech enhancement (SE) at low signal-to noise ratios (SNR). Current speech enhancement solutions performed badly under low SNR situations. Loizou and Kim proposed a solution to reduce speech distortion errors in time-frequency (T-F) domain but it requires the knowledge of ground truth. As ground truth is unknown in real-life applications, the current study proposes to use a Bi-RNN to implement Loizou and Kim’s solution as a post-processing method for SE engines. Our solutions do not require prior knowledge of ground truth. The effectiveness of the proposed method is investigated with a spectral subtraction (SS) SE engine, a non-negative matrix factorization (NMF) SE engine, and a deep neural network ideal ratio mask (DNN-IRM) SE engine, under matched/mis-matched noise and different SNR conditions. Experimental results demonstrate that the proposed post-processing method effectively improved both perceptual evaluation of speech quality (PESQ) and short-time objective intelligibility (STOI) for all of these SE engines, especially at low SNR conditions.