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.

Conventional approaches to the control of acoustic waves propagating along boundaries between fluids and hard grooved surfaces are limited to the manipulation of surface geometry. Here we demonstrate for the first time, through theoretical analysis, numerical simulation as well as experimentally, that the velocity of acoustic surface waves, and consequently the direction of their propagation as well as the shape of their wave fronts, can be controlled by varying the temperature distribution over the surface. This significantly increases the versatility of applications such as sound trapping, acoustic spectral analysis and acoustic focusing, by providing a simple mechanism for modifying their behavior without any change in the geometry of the system. We further discuss that the dependence between the behavior of acoustic surface waves and the temperature of the fluid can be exploited conversely as well, which opens a way for potential application in the domain of temperature sensing.

In this paper the research related to the development of a deep neural network based speech synthesizer for the Serbian language, trained on recorded utterances of a single female voice talent, is described. Two separate networks are used for prediction of acoustic features and phonetic segment durations. Through a set of experiments the optimal values of the hyper-parameters of the neural networks are established, and then the influence of the amount of training data on the quality of synthesized speech is examined. The quality is evaluated through objective measures as well as appropriate listening tests. It has been confirmed that 4-layer deep neural networks with 512 units per hidden layer, trained on 3 hours of data, produce speech of very good quality. The results also suggest that a further increase in the amount of training data may contribute to further improvement in quality.

The paper presents a novel architecture and method for training neural networks to produce synthesized speech in a particular voice and speaking style, based on a small quantity of target speaker/style training data. The method is based on neural network embedding, i.e. mapping of discrete variables into continuous vectors in a low-dimensional space, which has been shown to be a very successful universal deep learning technique. In this particular case, different speaker/style combinations are mapped into different points in a low-dimensional space, which enables the network to capture the similarities and differences between speakers and speaking styles more efficiently. The initial model from which speaker/style adaptation was carried out was a multi-speaker/multi-style model based on 8.5 hours of American English speech data which corresponds to 16 different speaker/style combinations. The results of the experiments show that both versions of the obtained system, one using 10 minutes and the other as little as 30 seconds of target data, outperform the state of the art in parametric speaker/style-dependent speech synthesis. This opens a wide range of application of speaker/style dependent speech synthesis based on small quantities of training data, in domains ranging from customer interaction in call centers to robot-assisted medical therapy.