Communication has been an important aspect of human life, civilization, and globalization for thousands of years. Biometric analysis, education, security, healthcare, and smart cities are only a few examples of speech recognition applications. Most studies have mainly concentrated on English, Spanish, Japanese, or Chinese, disregarding other low-resource languages, such as Uzbek, leaving their analysis open. In this paper, we propose an End-To-End Deep Neural Network-Hidden Markov Model speech recognition model and a hybrid Connectionist Temporal Classification (CTC)-attention network for the Uzbek language and its dialects. The proposed approach reduces training time and improves speech recognition accuracy by effectively using CTC objective function in attention model training. We evaluated the linguistic and lay-native speaker performances on the Uzbek language dataset, which was collected as a part of this study. Experimental results show that the proposed model achieved a word error rate of 14.3% using 207 h of recordings as an Uzbek language training dataset.

Automatic speech recognition systems with a large vocabulary and other natural language processing applications cannot operate without a language model. Most studies on pre-trained language models have focused on more popular languages such as English, Chinese, and various European languages, but there is no publicly available Uzbek speech dataset. Therefore, language models of low-resource languages need to be studied and created. The objective of this study is to address this limitation by developing a low-resource language model for the Uzbek language and understanding linguistic occurrences. We proposed the Uzbek language model named UzLM by examining the performance of statistical and neural-network-based language models that account for the unique features of the Uzbek language. Our Uzbek-specific linguistic representation allows us to construct more robust UzLM, utilizing 80 million words from various sources while using the same or fewer training words, as applied in previous studies. Roughly sixty-eight thousand different words and 15 million sentences were collected for the creation of this corpus. The experimental results of our tests on the continuous recognition of Uzbek speech show that, compared with manual encoding, the use of neural-network-based language models reduced the character error rate to 5.26%.

In this paper has been discussed about speech recognition using spectrogram images and deep convolution neural network(CNN) of Uzbek spoken digits. Spectrogram images from speech signal were generated and it were used for deep CNN training. Presented CNN model contains 3 convolution layers and 2 fully connected layers that discriminative features can be divided and estimated of spectrogram images by those layers. In current research period, dataset of Uzbek spoken digits were made and in based on presented CNN model they were trained. Testing results shows that, proposed approach for Uzbek spoken digits classified 100% accuracy.

Currently, speech recognition systems are becoming more widespread, especially in those applications where speech dialogue is the most convenient mean of information control and exchange with technical facilities. Obtaining an effective voice control system is currently an important task, requiring the development of methods to obtain high recognition accuracy of voice commands. Under these conditions, along with reducing the noise effect on the quality of recognition, the task is to increase the accuracy in voice control system operation, to increase the likelihood of correct command recognition under stationary interference. Another requirement in the voice control system is the correct recognition speed, since the system must work in real time. In this paper, we propose an algorithm for voice control by technical facilities, based on Uzbek language. Some sounds in Uzbek language (explosive and unvoiced consonants) differ strongly from the sounds in other languages; when creating control algorithms, the recognition accuracy does not meet the requirements. Therefore, to ensure the necessary processing speed and maintain the required accuracy, it is proposed to introduce an additional normalization with a decrease in feature space. The algorithm is based on the principle of primary separation of speech signal spectral characteristics. Further, the signal spectrum is normalized and its resolution increases due to the use of low-frequency conversion and logarithms. The obtained cepstral coefficients are fed to the input of a previously learned neural network.

Sound event detection tasks are rapidly advancing in the field of pattern recognition, and deep learning methods are particularly well suited for such tasks. One of the important directions in this field is to detect the sounds of emotional events around residential buildings in smart cities and quickly assess the situation for security purposes. This research presents a comprehensive study of an ensemble convolutional recurrent neural network (CRNN) model designed for sound event detection (SED) in residential and public safety contexts. The work focuses on extracting meaningful features from audio signals using image-based representation, such as Discrete Cosine Transform (DCT) spectrograms, Cocheagrams, and Mel spectrograms, to enhance robustness against noise and improve feature extraction. In collaboration with police officers, a two-hour dataset consisting of 112 clips related to four classes of emotional sounds, such as harassment, quarrels, screams, and breaking sounds, was prepared. In addition to the crowdsourced dataset, publicly available datasets were used to broaden the study’s applicability. Our dataset contains 5055 audio files of different lengths totaling 14.14 h and strongly labeled data. The dataset consists of 13 separate sound categories. The proposed CRNN model integrates spatial and temporal feature extraction by processing these spectrograms through convolution and bi-directional gated recurrent unit (GRU) layers. An ensemble approach combines predictions from three models, achieving F1 scores of 71.5% for segment-based metrics and 46% for event-based metrics. The results demonstrate the model’s effectiveness in detecting sound events under noisy conditions, even with a small, unbalanced dataset. This research highlights the potential of the model for real-time audio surveillance systems using mini-computers, offering cost-effective and accurate solutions for maintaining public order.