Automatic Recognition of Uzbek Speech Based on Integrated Neural Networks

Musaev, Muhammadjon; Khujayorov, Ilyos; Ochilov, Mannon

doi:10.1007/978-3-030-68004-6_28

Cited by 7 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Earlier efforts focused on the creation of Uzbek speech recognition in the context of the Uzbek language. For example, an initial Uzbek speech corpus consisting of 3500 utterances [ 8 ] was developed. In 2021, Musaev et al [ 33 ] proposed an HMM and DNN-based ASR system for the Uzbek language.…”

Section: Related Workmentioning

confidence: 99%

“…Although technological giants such as Google, Apple, Facebook, Microsoft, Amazon, and International Business Machines (IBM) have built advanced speech recognition engines for English, European, and Asian languages, research on ASR system development in most Central Asian languages such as Uzbek is still in its initial stages. This is due to the lack of a standard Uzbek language speech corpus, as well as dialectal differences [ 8 ]. First, Central Asian languages currently lack the minimum speech corpus required for the development of an ASR system.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Speech Recognition Method Based on Deep Learning Approaches for Uzbek Language

Mukhamadiyev

Khujayorov

Djuraev

et al. 2022

Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Automatic Speech Recognition Method Based on Deep Learning Approaches for Uzbek Language

Mukhamadiyev

Khujayorov

Djuraev

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…In the context of the Uzbek language, some works have previously attempted Uzbek speech recognition. For example, Musaev et al [23] developed an ASR system for geographical entities using a dataset consisting of 3,500 utterances. Similarly, the authors of [21] developed a read speech recognition system using 10 hours of transcribed audio.…”

Section: Related Workmentioning

confidence: 99%

“…Previously, several works have addressed Uzbek speech recognition [21,23]. However, to the best of our knowledge, there has been no work presenting an open-source Uzbek speech corpus of high quality and sufficient size for training robust speech recognition systems.…”

Section: Introductionmentioning

confidence: 99%

USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments

Musaev¹,

Mussakhojayeva²,

Khujayorov³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present a freely available speech corpus for the Uzbek language and report preliminary automatic speech recognition (ASR) results using both the deep neural network hidden Markov model (DNN-HMM) and end-to-end (E2E) architectures. The Uzbek speech corpus (USC) comprises 958 different speakers with a total of 105 hours of transcribed audio recordings. To the best of our knowledge, this is the first open-source Uzbek speech corpus dedicated to the ASR task. To ensure high quality, the USC has been manually checked by native speakers. We first describe the design and development procedures of the USC, and then explain the conducted ASR experiments in detail. The experimental results demonstrate promising results for the applicability of the USC for ASR. Specifically, 18.1% and 17.4% word error rates were achieved on the validation and test sets, respectively. To enable experiment reproducibility, we share the USC dataset, pre-trained models, and training recipes in our GitHub repository 1 .

show abstract

“…Although technology giants such as Google, Apple, Facebook, Microsoft, Amazon and IBM have built advanced speech recognition engines for English, European and Asian languages, research on ASR systems for most Central Asian languages such as Uzbek is still in its infancy [ 16 ]. The reason for this status is the lack of standard corpora and the existence of dialect differences [ 17 ]. Although a series of studies have been carried out under the condition of a lack of resources [ 18 , 19 , 20 ], the challenge of poor generalization ability and high error rate due to the scarcity of resources still exists under the condition of low resources.…”

Section: Introductionmentioning

confidence: 99%

Improving Hybrid CTC/Attention Architecture for Agglutinative Language Speech Recognition

Ren

Yolwas

Slamu

et al. 2022

Sensors

View full text Add to dashboard Cite

Unlike the traditional model, the end-to-end (E2E) ASR model does not require speech information such as a pronunciation dictionary, and its system is built through a single neural network and obtains performance comparable to that of traditional methods. However, the model requires massive amounts of training data. Recently, hybrid CTC/attention ASR systems have become more popular and have achieved good performance even under low-resource conditions, but they are rarely used in Central Asian languages such as Turkish and Uzbek. We extend the dataset by adding noise to the original audio and using speed perturbation. To develop the performance of an E2E agglutinative language speech recognition system, we propose a new feature extractor, MSPC, which uses different sizes of convolution kernels to extract and fuse features of different scales. The experimental results show that this structure is superior to VGGnet. In addition to this, the attention module is improved. By using the CTC objective function in training and the BERT model to initialize the language model in the decoding stage, the proposed method accelerates the convergence of the model and improves the accuracy of speech recognition. Compared with the baseline model, the character error rate (CER) and word error rate (WER) on the LibriSpeech test-other dataset increases by 2.42% and 2.96%, respectively. We apply the model structure to the Common Voice—Turkish (35 h) and Uzbek (78 h) datasets, and the WER is reduced by 7.07% and 7.08%, respectively. The results show that our method is close to the advanced E2E systems.

show abstract

Automatic Recognition of Uzbek Speech Based on Integrated Neural Networks

Cited by 7 publications

References 11 publications

Automatic Speech Recognition Method Based on Deep Learning Approaches for Uzbek Language

Automatic Speech Recognition Method Based on Deep Learning Approaches for Uzbek Language

USC: An Open-Source Uzbek Speech Corpus and Initial Speech Recognition Experiments

Improving Hybrid CTC/Attention Architecture for Agglutinative Language Speech Recognition

Contact Info

Product

Resources

About