Speech technologies have been developed for decades as a typical signal processing area, while the last decade has brought a huge progress based on new machine learning paradigms. Owing not only to their intrinsic complexity but also to their relation with cognitive sciences, speech technologies are now viewed as a prime example of interdisciplinary knowledge area. This review article on speech signal analysis and processing, corresponding machine learning algorithms, and applied computational intelligence aims to give an insight into several fields, covering speech production and auditory perception, cognitive aspects of speech communication and language understanding, both speech recognition and text-to-speech synthesis in more details, and consequently the main directions in development of spoken dialogue systems. Additionally, the article discusses the concepts and recent advances in speech signal compression, coding, and transmission, including cognitive speech coding. To conclude, the main intention of this article is to highlight recent achievements and challenges based on new machine learning paradigms that, over the last decade, had an immense impact in the field of speech signal processing.

In this paper a detail analysis of speech coding algorithm based on forward adaptive technique is carried out. We consider an algorithm that works on frame-by-frame basis, where a frame consists of a certain number of speech samples. Buffering frame-by-frame an estimation of the gain defined as squared root of the frame variance is enabled. The information about the gain (side information) and the code book of a nonadaptive quantizer, which is designed for the unit variance case of the input signal, are further used when designing an adaptive quantizer. In such a way better quantizer adaptation to the varying input statistics is provided. Observe that the goal of this paper is to investigate the preference that for the wide range of variance change could be achieved when implementing in the forward adaptive speech coding algorithm, the recently developed effective method for the Lloyd–Max's algorithm initialization, which provides optimal Lloyd–Max's quantizer performances for the unit variance case of the input signal. We destine to consider the speech coding algorithm based on forward adaptive technique since the backward adaptation provides SQNR (signal to quantization noise ratio) within 1 dB of the forward adaptation. We provide theoretical and experimental results (performances of our algorithm) which are compared with the optimal results. Additionally, we discuss the performances of speech coding schemes designed according to G. 711 standard and we point out the benefits that can be achieved by using our algorithm. Finally, in order to find better solution for implementation of the proposed algorithm in practice we consider the performances of our algorithm when log-uniform as well as uniform scalar quantizer are used for gain quantizing.

This paper contributes to the goal of finding an efficient compression solution for post-training quantization from the perspective of support region choice under the framework of low-bit uniform quantization. The decision to give preference to uniform quantization comes from the fact that support region choice is the most sensitive in the uniform quantization of nonuniform sources (e.g., Laplacian sources). Therefore, in this paper, we analyse in detail how the choice of the support region influences the performance of two-bits uniform quantization, measured with signal to quantization noise ratio (SQNR), and the accuracy of the compressed neural network (NN) model. We provide experimental and theoretical results for a few significant cases of two-bits uniform quantizer design, where we assume that Laplacian source models the distribution of weights in our fully connected NN. We opt for Laplacian distribution since it models well weights of NNs. Specifically, we analyse whether it is possible to apply the simplest uniform quantization in trained NN model weight representation with a bit rate of R=2 bit/sample while preserving the accuracy of the model to a great extent. Also, our goal is to determine whether the choice of the key parameter of two-bits uniform quantizer (support region threshold) equally reflects on both, SQNR and accuracy. Moreover, we extend our analysis to the application of layer-wise two-bits uniform quantization in order to examine whether it is possible to achieve an additional improvement of the accuracy of our NN model for the MNIST dataset. We believe that the detailed analysis of post-training quantization described and conducted in this paper is very useful for all further research studies of this very current topic, especially due to the fact that the problem regarding post-training quantization is addressed from a particularly important perspective of choosing the support region.

Driven by the need for the compression of weights in neural networks (NNs), which is especially beneficial for edge devices with a constrained resource, and by the need to utilize the simplest possible quantization model, in this paper, we study the performance of three-bit post-training uniform quantization. The goal is to put various choices of the key parameter of the quantizer in question (support region threshold) in one place and provide a detailed overview of this choice’s impact on the performance of post-training quantization for the MNIST dataset. Specifically, we analyze whether it is possible to preserve the accuracy of the two NN models (MLP and CNN) to a great extent with the very simple three-bit uniform quantizer, regardless of the choice of the key parameter. Moreover, our goal is to answer the question of whether it is of the utmost importance in post-training three-bit uniform quantization, as it is in quantization, to determine the optimal support region threshold value of the quantizer to achieve some predefined accuracy of the quantized neural network (QNN). The results show that the choice of the support region threshold value of the three-bit uniform quantizer does not have such a strong impact on the accuracy of the QNNs, which is not the case with two-bit uniform post-training quantization, when applied in MLP for the same classification task. Accordingly, one can anticipate that due to this special property, the post-training quantization model in question can be greatly exploited.

The Gaussian Q-function has considerable applications in numerous areas of science and engineering. However, the fact that a closed-form expression for this function does not exist encourages finding approximations or bounds of the Q-function. In this paper, we determine analytically two novel interval upper bound Q-function approximations and show that they could be used efficiently not only for the symbol error probability (SEP) estimation of transmission over Nakagami-m fading channels, but also for the average symbol error probability (ASEP) evaluation for two modulation formats. Specifically, we determine analytically the composition of the upper bound Q-function approximations specified at disjoint intervals of the input argument values so as to provide the highest accuracy within the intervals, by utilizing the selected one of two upper bound Q-function approximations. We show that a further increase of the accuracy, achieved in the case with two upper-bound approximations composing the interval approximation, can be obtained by forming a composite interval approximation of the Q-function that assumes another extra interval and by specifying the third form for the upper-bound Q-function approximation. The proposed analytical approach can be considered universal and widely applicable. The results presented in the paper indicate that the proposed Q-function approximations outperform in terms of accuracy other well-known approximations carefully chosen for comparison purposes. This approximation can be used in numerous theoretical communication problems based on the Q-function calculation. In this paper, we apply it to estimate the average bit error rate (ABER), when the transmission in a Nakagami-m fading channel is observed for the assumed binary phase-shift keying (BPSK) and differentially encoded quadrature phase-shift keying (DE-QPSK) modulation formats, as well as to design scalar quantization with equiprobable cells for variables from a Gaussian source.

The approximations for the Q‐function reported in the literature so far have mainly been developed to overcome not only the difficulties, but also the limitations, caused in different research areas, by the nonexistence of the closed form expression for the Q‐function. Unlike the previous papers, we propose the novel approximation for the Q‐function not for solving some particular problem. Instead, we analyze this problem in one general manner and we provide one general solution, which has wide applicability. Specifically, in this paper, we set two goals, which are somewhat contrary to each other. The one is the simplicity of the analytical form of Q‐function approximation and the other is the relatively high accuracy of the approximation for a wide range of arguments. Since we propose a two‐parametric approximation for the Q‐function, by examining the effect of the parameters choice on the accuracy of the approximation, we manage to determine the most suitable parameters of approximation and to achieve these goals simultaneously. The simplicity of the analytical form of our approximation along with its relatively high accuracy, which is comparable to or even better than that of the previously proposed approximations of similar analytical form complexity, indicates its wide applicability.