This paper presents the research and development of the prototype of the assistive mobile information robot (AMIR). The main features of the presented prototype are voice and gesture-based interfaces with Russian speech and sign language recognition and synthesis techniques and a high degree of robot autonomy. AMIR prototype’s aim is to be used as a robotic cart for shopping in grocery stores and/or supermarkets. Among the main topics covered in this paper are the presentation of the interface (three modalities), the single-handed gesture recognition system (based on a collected database of Russian sign language elements), as well as the technical description of the robotic platform (architecture, navigation algorithm). The use of multimodal interfaces, namely the speech and gesture modalities, make human-robot interaction natural and intuitive, as well as sign language recognition allows hearing-impaired people to use this robotic cart. AMIR prototype has promising perspectives for real usage in supermarkets, both due to its assistive capabilities and its multimodal user interface.

The paper presents a concept of a smart robotic trolley for supermarkets with a multimodal user interface, including sign language and acoustic speech recognition, and equipped with a touchscreen. Considerable progress in hand gesture recognition and automatic speech recognition within the last years has brought to life many human-computer interaction systems. At the moment the level of voiced speech and isolated/static hand gesture automatic recognition quality is quite high. However, continuous or dynamic sign language recognition still remains an unresolved challenge. There exists no automatic recognition system for Russian sign language nowadays. There are also no relevant data for model training. In the present research, we try to fill in this gap for the Russian sign language. We present a Kinect 2.0 based software-hardware complex for collection of multimodal sign language databases with an optical video camera, infrared camera and depth sensor. We describe the architecture of the developed software as well as some details of the collected database. The collected corpus is meant for further development of a Russian sign language recognition system, which will be embedded into a robotic trolley for supermarkets with gestural and speech interfaces. The architecture of the developed system is also presented in the paper.

In this paper, we propose an approach to detect and recognize 3D one-handed gestures for human-machine interaction. The logical structure of the modules of the system for recording a gestural database is described. The logical structure of the database of 3D gestures is presented. Examples of frames showing gestures in the format of Full High Definition, in the map depth mode and in the infrared illustrated. Models of a deep convolutional network for detecting faces and hand shapes are described. The results of automatic detection of the area with the face and the shape of the hand are given. Identified the distinctive features of the gesture at a certain point in time. The process of recognizing 3D one-handed gestures is described. Due to its versatility, this method can be used in tasks of biometrics, computer vision, machine learning, automatic systems of face recognition, sign languages.

Recently, there has been a growth in the number of studies addressing the automatic processing of low-resource languages. The lack of speech and text data significantly hinders the development of speech technologies for such languages. This paper introduces an automatic speech recognition system for Livvi-Karelian. Acoustic models based on artificial neural networks with time delays and hidden Markov models were trained using a limited speech dataset of 3.5 h. To augment the data, pitch and speech rate perturbation, SpecAugment, and their combinations were employed. Language models based on 3-grams and neural networks were trained using written texts and transcripts. The achieved word error rate metric of 22.80% is comparable to other low-resource languages. To the best of our knowledge, this is the first speech recognition system for Livvi-Karelian. The results obtained can be of a certain significance for development of automatic speech recognition systems not only for Livvi-Karelian, but also for other low-resource languages, including the fields of speech recognition and machine translation systems. Future work includes experiments with Karelian data using techniques such as transfer learning and DNN language models.

In this paper, principal methods for solving training data issues for the so-called low-resource languages are discussed, regarding elaboration of automatic speech recognition systems. The notion of low-resource languages is studied and a working definition is coined on the basis of a number of papers on this topic. The main difficulties associated with the application of classical approaches to automatic speech recognition to the material of low-resource languages are determined, and the principal methods used to solve these problems are outlined. The paper discusses the methods for data augmentation, transfer learning and collection of new language data in detail. Depending on specific tasks, methods for audio material and text data augmentation, transfer learning and multi-task learning are distinguished. In Section 4 of the paper the current information support methods, databases and the basic principles of their architecture are discussed with regard to low-resource languages. Conclusions are drawn about the justification of augmentation and knowledge transfer methods for languages with low information support. In the case of unavailability of language data or structurally similar parent models, the preferred option is to collect a new database, including the crowdsourcing technique. Multilanguage learning models are effective for small datasets. If big language data are available, the most efficient method is transfer learning within a language pair. The conclusions made in the course of this this review will be applied to the data of the low-resource Karelian language, for which an automatic speech recognition system has been being created by the authors of this paper since the beginning of the year 2022.