Explore the vast range of titles available.

Speech coding is a method to reduce the amount of data needs to represent speech signals by exploiting the statistical properties of the speech signal. Recently, in the speech coding process, a neural network prediction model has gained attention as the reconstruction process of a nonlinear and nonstationary speech signal. This study proposes a novel approach to improve speech coding performance by using a gated recurrent unit (GRU)-based adaptive differential pulse code modulation (ADPCM) system. This GRU predictor model is trained using a data set of speech samples from the DARPA TIMIT Acoustic-Phonetic Continuous Speech Corpus actual sample and the ADPCM fixed-predictor output speech sample. Our contribution lies in the development of an algorithm for training the GRU predictive model that can improve its performance in speech coding prediction and a new offline trained predictive model for speech decoder. The results indicate that the proposed system significantly improves the accuracy of speech prediction, demonstrating its potential for speech prediction applications. Overall, this work presents a unique application of the GRU predictive model with ADPCM decoding in speech signal compression, providing a promising approach for future research in this field.

The Adaptive Differential Pulse Code Modulation (ADPCM) has been standardized by the International Telecommunication Union (ITU) due to its significance and extensive applications within telecommunication networks. This paper provides a concise overview of the recent US patents related to ADPCM, covering the years 2024 to 2025. Additionally, the general architecture of ADPCM is discussed. The findings presented herein aim to inspire researchers and motivate further explorations in this domain.

Hyperspectral imaging is known for its rich spatial–spectral information. The spectral bands provide the ability to distinguish substances spectra which are substantial for analyzing materials. However, high-dimensional data volume of hyperspectral images is problematic for data storage. In this paper, we present a lossy hyperspectral image compression system based on the regression of 3D wavelet coefficients. The 3D wavelet transform is applied to sparsely represent the hyperspectral images (HSI). A support vector machine regression is then applied on wavelet details and provides vector supports and weights which represent wavelet texture features. To achieve the best possible overall rate-distortion performance after regression, entropy encoding based on run-length encoding and arithmetic encoding is used. To preserve the spatial pertinent information of the image, the lowest sub-band wavelet coefficients are furthermore encoded by a lossless coding with differential pulse code modulation. Spectral and spatial redundancies are thus substantially reduced. Experimental tests are performed over several HSI from airborne and spaceborne sensors and compared with the main existing algorithms. The obtained results show that the proposed compression method has high performances in terms of rate distortion and spectral fidelity. Indeed, high PSNRs and classification accuracies, which could exceed 40.65 dB and 75.8 % , respectively, are observed for all decoded HSI images and overpass those given by many cited famous methods. In addition, the evaluation of detection and compression over various bands shows that spectral information is preserved using our compression method.

The digital voice is multimedia content of great importance, given the range of applications where it can be found. This paper addresses the shortcomings of existing voice authentication algorithms, presenting a completely blind speech authentication and recovery method based on fragile watermarking using the Least Significant Bit (LSB) method. This scheme obtains a compressed version of the original speech signal by Adaptive Differential Pulse Code Modulation (ADPCM) coding and the Discrete-Time Wavelet Transform (DTWT). Authentication bits are then generated by the SHA256 hash function, and the watermark is afterward embedded in the last three LSBs of the original audio samples. Experimental results evaluated on five different audio databases, each comprising speech signals recorded in different situations, contexts, and languages, have demonstrated a high embedding payload and imperceptibility of the watermark, obtaining an average Signal-to-Noise Ratio (SNR) value above 40 d B . Furthermore, the proposed method demonstrates a strong ability to accurately locate and restore up to 50% of a speech signal that has been tampered with, using no additional information. Moreover, the recovered speech signal is intelligible and has an SNR value higher than other recovery schemes, justifying the efficiency of the proposed method.

Image Compressive Sensing (CS) provides a scheme of low-complex image coding, but coping with the recovery quality has been a challenge. Even the excessive investment of computations into recovery cannot prevent the quality degradation due to the lack of appropriate allocation for sampling resources. In light of this, this paper fuses a context-based allocation into image CS in order to improve the recovery quality with fewer computations. Independent of original pixels, the context features of blocks are extracted from random CS samples. According to the block-based distribution on context features, more CS samples are allocated to non-sparse regions and fewer to sparse regions. The proposed context-based allocation enables a linear recovery model to accurately recover images. The contributions of this paper include: (1) an adaptive allocation involving the context features extracted from CS samples, (2) a padding Differential Pulse Code Modulation (DPCM) to quantize the adaptive CS samples, and (3) a regrouping module to improve the quality of linear recovery. Experimental results show the proposed image CS system objectively and subjectively improves the recovery quality of an image while guaranteeing a low computational complexity, e.g., it achieves average 30.85 dB PSNR value on the five 512 × 512 test images, and costs about 10 seconds on a computer with 3.30 GHz CPU and 8 GB RAM. Besides, the proposed system presents a competitive performance to the recent deep-learned image CS systems.

With the rapid development of hyperspectral remote sensing technology, the spatial resolution and spectral resolution of hyperspectral images are continually increasing, resulting in a continual increase in the scale of hyperspectral data. At present, hyperspectral lossless compression technology has reached a bottleneck. Simultaneously, the rise of deep learning has provided us with new ideas. Therefore, this paper examines the use of deep learning for the lossless compression of hyperspectral images. In view of the differential pulse code modulation (DPCM) method being insufficient for predicting spectral band information, the proposed method, called C-DPCM-RNN, uses a deep recurrent neural network (RNN) to improve the traditional DPCM method and improve the generalization ability and prediction accuracy of the model. The final experimental result shows that C-DPCM-RNN achieves better compression on a set of calibrated AVIRIS test images provided by the Multispectral and Hyperspectral Data Compression Working Group of the Consultative Committee for Space Data Systems in 2006. C-DPCM-RNN overcomes the limits of traditional methods in its performance on uncalibrated AVIRIS test images.

In this paper, a simple image compression algorithm is proposed for wireless capsule endoscopy. The proposed algorithm consists of new simplified YUV colour space, corner clipping, uniform quantization, subsampling, differential pulse code modulation and Golomb Rice code. Simplified YUV colour space is proposed based on special nature of endoscopic images and provide good results. The quantization and subsampling are used as lossy compression techniques and fixed Golomb-Rice code is used to encode residual value obtained after differential pulse code modulation operation. Here performance of different combination of quantization and subsampling techniques are analyzed based combination along with the proposed compression algorithm provides compression ratio of 89.3% and peak signal noise ratio of 45.1. the proposed algorithm provided better results as compared to various reported algorithms in literature in term of CR and PSNR.

Using an image compression hybrid model, the suggested research created a practical method for integrating learning system advantages with a decision logic framework. The emphasis here is that when integrated with the conventional image coding technology the potential usefulness of the decision logic is used as decision making. The execution is divided into three stages. In the first place, the image DCT representation of the image transformed to a different energy usage and is computed for different energy levels. A parallel processing of each power coefficient would then result in a substantially higher processing speed. In the second phase, differential pulse code modulation is used to compress the coefficients that correspond to the lowest energy level. Coefficients from the learning system are used as energy component, used to extract the coefficients. Finally, the algorithm is fed the results of the probabilistic decisions made in the second step of the program’s development. To validate the proposed approach, the suggested method is tested over different Magnetic resonance imaging (MRI) medical samples. The simulation findings reveal good results and suggest that the reconstructed images are better than the conventional system. The developed Neuro-Fuzzy image compression model, results in attaining high accuracy and precision with reduced processing overhead and computation complexity.

Both traditional frequency modulation and phase modulation digital modulation methods have low spectral utilization, poor multipath fading resistance, slow power spectrum attenuation, and severe out-of-band radiation. Quadrature Amplitude Modulation (QAM) is a digital modulation technique that combines phase and amplitude control. It not only achieves higher spectral efficiency, but also transmits higher rate data in a defined frequency band. In this paper, the basic principle, system structure and performance parameters of QAM modulation and demodulation are studied in depth to realize simulink simulation and performance analysis of QAM modulation and demodulation system. The basic theory and implementation method of analog signal digitization are analyzed in detail to realize simimlink of differential pulse code modulation. Based on the above theory, the analog source QAM transmission system is constructed, and simulink is used for modeling and simulation and performance verification.The simulation results show that the constructed QAM digital transmission system can achieve good transmission of analog signals.

Video compression has great significance in the communication of motion pictures. Video compression techniques try to remove the different types of redundancy within or between video sequences. In the temporal domain, the video compression techniques remove the redundancies between the highly correlated consequence frames of the video. In the spatial domain, the video compression techniques remove the redundancies between the highly correlated consequence pixels (samples) in the same frame. Evolving neural-networks based video coding research efforts are focused on improving existing video codecs by performing better predictions that are incorporated within the same codec framework or holistic methods of end-to-end video compression schemes. Current neural network-based video compression adapts static codebook to achieve compression that leads to learning inability from new samples. This paper proposes a modified video compression model that adapts the genetic algorithm to build an optimal codebook for adaptive vector quantization that is used as an activation function inside the neural network’s hidden layer. Background subtraction algorithm is employed to extract motion objects within frames to generate the context-based initial codebook. Furthermore, Differential Pulse Code Modulation (DPCM) is utilized for lossless compression of significant wavelet coefficients; whereas low energy coefficients are lossy compressed using Learning Vector Quantization (LVQ) neural networks. Finally, Run Length Encoding (RLE) is engaged to encode the quantized coefficients to achieve a higher compression ratio. Experiments have proven the system’s ability to achieve higher compression ratio with acceptable efficiency measured by PSNR.