Kazakh NLP Atlas

Kazakh is underrepresented in resources for evaluating the safety behavior of large language models. We present KZ-SafetyPrompts, a Kazakh prompt dataset for safety evaluation across eleven categories covering common risk areas such as self-harm, violence, ch…

Introduction This study presents a bidirectional communication system designed to enhance interaction between hearing-impaired and hearing individuals using gesture recognition. Methods The proposed framework integrates multiple components, including Kazakh S…

Sign languages are natural, visual-gestural languages used by Deaf communities worldwide. Over 300 distinct sign languages remain severely low-resource due to limited documentation, sparse datasets, and insufficient computational tools. This systematic review…

We present a new publicly available corpus of 100,502 movie reviews from Kazakhstan collected from kino.kz, spanning 2001-2025 and covering 4,943 unique titles. The dataset is multilingual, consisting mainly of Russian reviews alongside Kazakh and code-switch…

This paper investigates Multilingual Medical Question Answering across high-resource (English, Spanish, French, Italian) and low-resource (Basque, Kazakh) languages. We evaluate three types of external evidence sources across models of varying size: curated r…

The Kazakh language is hard for learners and machine translation because of its complicated morphology, regional differences, and subtle differences in meaning. This research presents a crowdsourcing-driven adaptive translation system that amalgamates automat…

This paper suggests a structure that can guide the enhancement of the Kazakh language learning process by using the large language models (LLMs) and automatic speech recognition (ASR). To fill the gap of highquality speech materials on the Kazakh language, a …

Kazakh sequence labeling is constrained by limited annotated resources, while its agglutinative morphology and productive suffixation increase data sparsity and exacerbate label inconsistency in part-of-speech (POS) tagging and named entity recognition (NER).…

Large pre-trained speech models similar to Whisper are now commonly used for speech recognition and related tasks. The distribution of paralinguistic features, which include emotions and speaker characteristics across model layers, remains uncertain, particul…

Speech-to-text translation (S2TT) for low-resource languages remains challenging due to the scarcity of parallel speech translation data and the susceptibility of modular pipelines to error propagation. This paper presents a controlled empirical comparison of…

The rapid expansion of translation technologies has transformed both professional translation practice and translator education. In languages with developing digital infrastructures, such as Kazakh, the integration of machine translation and computer-assisted…

This study examines the challenge of automatically transcribing multilingual institutional speech in Kazakhstan, where speakers frequentlбукy switch between Kazakh, Russian, and English. While modern automatic speech recognition (ASR) systems achieve high acc…

Large language models fragment Kazakh text into many more tokens than equivalent English text, because their tokenizers were built for high-resource languages. This tokenizer tax inflates compute, shortens the effective context window, and weakens the model's…

We investigate how large language models perform on low-resource languages by benchmarking eight LLMs across five experimental conditions in English, Kazakh, and Mongolian. Using 50 hand-crafted questions spanning factual, reasoning, technical, and culturally…

Kazakh, a Turkic language spoken by over 22 million people, remains underserved by existing multilingual language models, which allocate minimal capacity to low-resource languages and employ tokenizers ill-suited to agglutinative morphology. We present SozKZ,…

This paper presents the first prototype of a speech-to-sign language translation system for Kazakh Sign Language (KRSL). The proposed pipeline integrates the NVIDIA FastConformer model for automatic speech recognition (ASR) in the Kazakh language and addresse…

Large language models (LLMs) have transformed natural language processing, yet their capabilities remain uneven across languages. Most multilingual models are trained primarily on high-resource languages, leaving many languages with large speaker populations …

Machine translation for low-resource languages such as Kazakh remains a complex task due to the scarcity of training data, intricate morphological structures, and culturally specific linguistic characteristics. This study presents the first extensive explorat…

Developing automatic speech recognition (ASR) systems for low-resource languages is hindered by the scarcity of transcribed corpora. This proof-of-concept study explores songs as an unconventional yet promising data source for Kazakh ASR. We curate a dataset …

Kazakh is a Turkic language using the Arabic, Cyrillic, and Latin scripts, making it unique in terms of optical character recognition (OCR). Work on OCR for low-resource Kazakh scripts is very scarce, and no OCR benchmarks or images exist for the Arabic and L…

The article examines the pedagogical features of integrating artificial intelligence (AI) technologies into the process of teaching Kazakh at higher education institutions. Artificial intelligence is viewed as a tool for enhancing the effectiveness of languag…

We explore machine translation for five Turkic language pairs: Russian-Bashkir, Russian-Kazakh, Russian-Kyrgyz, English-Tatar, English-Chuvash. Fine-tuning nllb-200-distilled-600M with LoRA on synthetic data achieved chrF++ 49.71 for Kazakh and 46.94 for Bash…

This study presents the application of free, open-source artificial intelligence (AI) techniques to advance machine translation for low-resource Turkic languages such as Kazakh, Azerbaijani, Kyrgyz, Turkish, Turkmen, and Uzbek. This machine translation proble…

This paper explores the impact of various synthetic data generation methods on the performance of speech separation and diarization models. Three approaches are considered: simple audio track overlay, synthetic dialogue generation, and acoustic condition mode…

This study is focused on improving the noise robustness of a biometric speaker identification system based on mel-frequency cepstral coefficients (MFCC) and a convolutional neural network (CNN). The object of analysis is the acoustic structure of the Kazakh l…

This article provides a comprehensive review of contemporary research in the field of natural language processing (NLP) and speech technologies for Central Asian Turkic languages, including Kazakh, Kyrgyz, and Uzbek. Although a number of theoretical and appli…

Разработка систем автоматического распознавания казахской речи остаётся актуальной задачей в условиях ограниченных языковых ресурсов и высокой морфологической сложности агглютинативных языков. Цель исследования заключается в сравнительном анализе локальных и …

In the field of speech recognition, end-to-end models are gradually replacing traditional and hybrid approaches. Their main principle is autoregressive decoding, where the output sequence is formed from left to right. However, it has not yet been proven that …

This article discusses the process of developing a Kazakh sign language recognition system using the MediaPipe platform. The platform allows for efficient real-time gesture recognition. The main focus is on creating models for gesture recognition, training ne…

Technologies for automatic processing of sign language have become an urgent need for members of society with hearing and speech impairments who face inequality in the era of digital transformation. In recent years, the issue of considering sign language as a…

This article provides a comprehensive analysis of effective strategies for enhancing the scientific and theoretical development of the Kazakh language through the integration of artificial intelligence technologies and linguistic corpora. The primary aim of t…

In low-resource speech recognition, the performance of the Whisper model is often limited by the size of the available training data. To address this challenge, this paper proposes a training optimization method for the Whisper model that integrates Low-Rank …

The development of parallel audio corpora for Turkic languages, such as Kazakh, Uzbek, and Tatar, remains a significant challenge in the development of multilingual speech synthesis, recognition systems, and machine translation. These languages are low-resour…

While the roles of human translators and machines have shifted with the development of such engines as Google Translate and DeepL, the issue of translating the untranslatable or culture-specific items from Kazakh into English still remain challenging. The lac…

Lip reading systems determine the content of speech based on the visual tracking of lips of the speaker and therefore serve to offer communicative substitutes when acoustic information is not available in the environment. The training of strong lip reading mo…

Machine Translation for English Retrieval of Information in Any Language (MATERIAL) is an IARPA initiative targeted to advance the state of cross-lingual information retrieval (CLIR). This report provides a detailed description of Information Sciences Institu…

We present a multilingual automatic speech recognition (ASR) system for Kazakh, Russian, and English designed for the trilingual community of Kazakhstan. Although prior research has shown that speech-based text entry can outperform conventional keyboard typin…

Multilingual Speech Command Recognition (SCR) facilitates voice interaction in environments where multiple languages are used interchangeably, a common characteristic of multilingual regions. In such settings, SCR and language identification (LID) are handled…

With the rapid development of artificial intelligence and machine learning technologies, automatic speech recognition (ASR) and text-to-speech (TTS) have become key components of the digital transformation of society. The Kazakh language, as a representative …

Machine translation for low-resource languages like Kazakh faces significant challenges due to limited training data, complex morphology, and cultural-linguistic nuances. This paper presents the first comprehensive study on fine-tuning large language models f…

Named entity transcription remains a challenge for low-resource languages such as Kazakh, often causing errors in proper nouns, locations, and other named entities. This paper presents a fine-tuning approach using OpenAI’s Whisper model, KazakhTTS2 and KazEmo…

This article presents a comprehensive study of automatic speech recognition (ASR) for Kazakh children's speech, with a particular focus on the impact of signal preprocessing techniques in a low-resource linguistic environment. Although commercial ASR systems …

This paper introduces a punctuation and capitalization (PC) restoration model for Kazakh, developed using the bert-base-multilingual-uncased model within NVIDIA’s NeMo framework. The model was trained on a curated dataset of preprocessed Kazakh Wikipedia arti…

Speech emotion recognition (SER) plays a crucial role in enhancing human–computer interaction by identifying emotional states in speech. However, low-resource languages like Kazakh face challenges due to limited datasets and linguistic tools. To address this …

This study presents a systematic comparison of two leading automatic speech recognition (ASR) model families—OpenAI's Whisper and Meta's SeamlessM4T—across three typologically diverse languages: English (Germanic), Russian (Slavic), and Kazakh (Turkic). Motiv…

This study explores fine-tuning methods and dataset structures for multilingual neural machine translation using the No Language Left Behind model, with a case study on Kazakh, English, and Russian. We compare single-stage and two-stage fine-tuning approaches…

The article presents a comprehensive overview of a probabilistic-statistical method for distinguishing homonyms in the process of compiling a frequency dictionary based on the Kazakh National Corpus. The research focuses on words that share identical written …

Currently, information technology is rapidly developing and one of its branches can be called machine translation. The use of machine translation in the process of understanding each other by people from different countries is increasing every year. At the mo…

In recent years, speech recognition technologies have significantly advanced due to artificial intelligence and machine learning methods. These technologies enable the automatic understanding of human speech and its conversion into text. The field of speech r…

This paper presents a novel fully autonomous multilingual audio transcription system tailored to Kazakh, Russian, and English. The proposed solution integrates a language detection module based on SpeechBrain with a transcription engine using Vosk, and employ…

This systematic review explores the importance of the Kazakh Sign Language (KSL) as the main method of communication for deaf and hard-of-hearing people in Kazakhstan. Despite its critical role, the automatic translation of KSL into spoken language remains un…

This study tackles NLP challenges in low-resource settings by developing the Small Kazakh Language Corpus—a high-quality, annotated collection of Kazakh texts sourced from news, scientific publications, and Wikipedia. The corpus was used to fine-tune two mode…

This paper presents the development of "DauysYm," an AI-powered translator that converts Kazakh Sign Language (KSL) into spoken language using dynamic gesture recognition. The project addresses communication barriers faced by people with hearing impairments i…

A fundamental component of natural language understanding, semantic role labeling (SRL) clarifies the relationship between predicates and their arguments, therefore enabling activities including information extraction, machine translation, and question answer…

Speech Command Recognition (SCR) has many applications in smart home systems, voice-controlled robots, and voice assistants. The modern SCR systems employ deep learning models trained on speech command datasets. Nowadays, the Google Speech Commands (GSC) data…

Multilingual automatic speech recognition (ASR) models greatly facilitate recognizing low-resource languages by sharing representations across similar languages. However, the commonly adopted modeling units, e.g., character-level modeling, lack language-speci…

The release of top-performing open-weight LLMs has cemented China's role as a leading force in AI development. Do these models support languages spoken in China? Or do they support the same languages as models developed in the United States or in Europe? Comp…

Machine translation for low resource language pairs is a challenging task. This task could become extremely difficult once a speaker uses code switching. We propose a method to build a machine translation model for code-switched Kazakh-Russian language pair w…

This article explores the methodology for evaluating the quality of simplified texts in Kazakh using BLEU and SARI metrics. Text simplification is an important aspect for ensuring information accessibility and facilitating the learning process in Kazakh langu…

Kazakh Sign Language (KSL) is a crucial communication tool for individuals with hearing and speech impairments. Deep learning, particularly Transformer models, offers a promising approach to improving accessibility in education and communication. This study a…

Llama-3.1-Sherkala-8B-Chat, or Sherkala-Chat (8B) for short, is a state-of-the-art instruction-tuned open generative large language model (LLM) designed for Kazakh. Sherkala-Chat (8B) aims to enhance the inclusivity of LLM advancements for Kazakh speakers. Ad…

Large language models (LLMs) excel in high-resource languages but struggle with low-resource languages (LRLs), particularly those spoken by minority communities in China, such as Tibetan, Uyghur, Kazakh, and Mongolian. To systematically track the progress in …

Instruction tuning in low-resource languages remains underexplored due to limited text data, particularly in government and cultural domains. To address this, we introduce and open-source a large-scale (10,600 samples) instruction-following (IFT) dataset, cov…

Large language models (LLMs) are known to have the potential to generate harmful content, posing risks to users. While significant progress has been made in developing taxonomies for LLM risks and safety evaluation prompts, most studies have focused on monoli…

Despite having a population of twenty million, Kazakhstan's culture and language remain underrepresented in the field of natural language processing. Although large language models (LLMs) continue to advance worldwide, progress in Kazakh language has been lim…

Being able to thoroughly assess massive multi-task language understanding (MMLU) capabilities is essential for advancing the applicability of multilingual language models. However, preparing such benchmarks in high quality native language is often costly and …

Automating real-time sign language translation through deep learning and machine learning techniques can greatly enhance communication between the deaf community and the wider public. This research investigates how these technologies can change the way indivi…

This article presents an overview of automatic speech recognition (ASR) technologies and describes the use of an advanced version of the Transformer model, the Hiformer model, in Kazakh speech recognition. A literature review of Kazakh speech recognition syst…

Kazakh is an agglutinative language, where the sequential attachment of morphemes forms words, each bearing specific grammatical information. The complexity of this morphological structure presents significant challenges for computational linguistics, particu…

This study offers a detailed evaluation of automatic speech recognition (ASR) systems for the Kazakh, examining their performance in recognizing the phonetic and linguistic features unique to the language. The Kazakh language presents specific challenges for …

This paper considers the problem of synonymous word detection in Kazakh using machine learning methods. The problem of automatic synonym detection is key to natural language processing tasks such as machine translation, context search, and semantic text analy…

This paper presents a hybrid approach to sentence alignment for the Kazakh-Turkish parallel corpus, addressing the challenges posed by linguistic and structural differences between the two languages. The system is divided into two modules: the Hunaling module…

This paper addresses the challenges of Named Entity Recognition (NER) in Kazakh speech, a critical task in Natural Language Processing (NLP). The integration of Automatic Speech Recognition (ASR) and NER technologies is explored to improve recognition accurac…

The development of machine translation is driven by the need for global communication through the automatic translation of words, sentences, and texts from one language to another. This paper proposes an improved Transformer-based model to enhance the perform…

Speaker verification interfaces are gaining more and more popularity in both academic and commercial industries. It's connected with the latest advances in this area, which can be seen firsthand in our daily life: voice interfaces in computers, robots, cell p…

The article describes the application of a transformer-based conformer model and a convolutional neural network (CNN) in Kazakh speech recognition, with an overview of automatic speech recognition (ASR) technologies. By exploring ways to combine convolutional…

Recent advancements in speech recognition technology have significantly enhanced accessibility and functionality across various sectors. Nonetheless, the task of recognizing kid’s speech presents considerable challenges. Children from different age groups exh…

The development of automated systems for the Kazakh language has gained significant momentum in recent years, driven by the growing need for natural language processing (NLP) tools tailored to underrepresented languages. This systematic review aims to critica…

The use of traditional IVR (Interactive Voice Response) methods often proves insufficient to meet customer needs. This article examines the application of artificial intelligence (AI) technologies to enhance the efficiency of IVR systems in call centers. A pr…

Whisper and other large-scale automatic speech recognition models have made significant progress in performance. However, their performance on many low-resource languages, such as Kazakh, is not satisfactory. It is worth researching how to utilize low-cost da…

Research in NLP for Central Asian Turkic languages - Kazakh, Uzbek, Kyrgyz, and Turkmen - faces typical low-resource language challenges like data scarcity, limited linguistic resources and technology development. However, recent advancements have included th…

Scientific research in the field of automated sign language translation represents a crucial stage in the development of technologies supporting the hearing-impaired and deaf communities. This article presents a comprehensive approach to addressing semantic a…

We survey the relevant literature on translation difficulty and automatic evaluation of machine translation (MT) quality and investigate whether source text’s translation difficulty features contain any information about MT quality. We analyse the 2017–2019 C…

This paper proposes SpecWav2vec-F, a novel model built upon the Wav2vec 2.0 baseline. The model demonstrates enhanced effectiveness in low-resource speech recognition tasks by preserving relationships between different time steps in the latent speech space. I…

Machine translation is a field of study that has attracted significant attention in recent years. The success of a model built on a language pair depends mainly on the number of parallel sentences between languages. Unlike high-resource languages, low-resourc…

The relevance of the problem of automatic speech recognition lies in the lack of research for low-resource languages, stemming from limited training data and the necessity for new technologies to enhance efficiency and performance. The purpose of this work wa…

The linguistic diversity of the Kazakh language poses unique challenges and opportunities for the development of automatic processing systems. This research explores a comprehensive array of methodologies employed in advancing automatic processing systems tai…

: Parallel corpora play a crucial role in the field of natural language processing, especially in tasks such as machine translation and cross-language information retrieval. However, with the increasing demand for more languages, the challenges are becoming i…

We introduce KazQAD -- a Kazakh open-domain question answering (ODQA) dataset -- that can be used in both reading comprehension and full ODQA settings, as well as for information retrieval experiments. KazQAD contains just under 6,000 unique questions with ex…

Sentiment analysis is an extensively explored domain within natural language processing (NLP); nevertheless, a significant emphasis has been placed on languages possessing ample resources, such as English. This paper delves into the transformative capabilitie…

This study focuses on the creation of the KazEmoTTS dataset, designed for emotional Kazakh text-to-speech (TTS) applications. KazEmoTTS is a collection of 54,760 audio-text pairs, with a total duration of 74.85 hours, featuring 34.23 hours delivered by a fema…

This study delves into the relatively unexplored domain of natural language processing for the Kazakh language—a language with limited computational resources. The paper dissects the effectiveness of diffusion models and transformers in generating text, speci…

We introduce KazParC, a parallel corpus designed for machine translation across Kazakh, English, Russian, and Turkish. The first and largest publicly available corpus of its kind, KazParC contains a collection of 371,902 parallel sentences covering different …

This paper presents KazSAnDRA, a dataset developed for Kazakh sentiment analysis that is the first and largest publicly available dataset of its kind. KazSAnDRA comprises an extensive collection of 180,064 reviews obtained from various sources and includes nu…

This paper presents a parallel corpus of raw texts between the Uzbek and Kazakh languages as a dataset for machine translation applications, focusing on the data collection process, dataset description, and its potential for reuse. The dataset-building proces…

In recent years, machine translation has made significant advancements; however, its effectiveness can vary widely depending on the language pair. Languages with limited resources, such as Kazakh, Uzbek, Kalmyk, Tatar, and others, often encounter challenges i…

Nowadays, speech-processing technologies with different language systems are successfully used in mobile and stationary devices. Kazakh is considered a low-resource language, which poses various challenges for conventional speech recognition methods. This pap…

Unsupervised Neural Machine Translation (UNMT) focuses on improving NMT results under the assumption there is no human translated parallel data, yet little work has been done so far in highlighting its advantages compared to supervised methods and analyzing i…

Speech Command Recognition (SCR) is rapidly gaining prominence due to its diverse applications, such as virtual assistants, smart homes, hands-free navigation, and voice-controlled industrial machinery. In this paper, we present a data-centric approach to cre…

With the advent of the Transformer architecture, Neural Machine Translation (NMT) results have shown great improvement lately. However, results in low-resource conditions still lag behind in both bilingual and multilingual setups, due to the limited amount of…

Current large language models demonstrate deficiencies in understanding low-resource languages, particularly the minority languages in China. This limitation stems from the scarcity of available pre-training data. To address this accessibility challenge, we p…

Automatic Speech Recognition (ASR) models can achieve human parity, but their performance degrades significantly when used in noisy industrial and urban environments. In this paper, we present monolingual and multilingual ASR models, which can perform effecti…

Low-resource languages often face the problem of insufficient data, which leads to poor quality in machine translation. One approach to address this issue is data augmentation. Data augmentation involves creating new data by transforming existing data through…

Nowadays, machine translation is considered to be a frequently used tool to render various types of texts related to such different spheres as science, film industry, etc. Statement of the problem: currently, as the higher school system in Kazakhstan starts i…

Speech translation systems have become indispensable in facilitating seamless communication across language barriers. This paper presents a cascade speech translation system tailored specifically for translating speech from the Kazakh language to Russian. The…

This study is devoted to the transcription of human speech in the Kazakh language in dynamically changing conditions. It discusses key aspects related to the phonetic structure of the Kazakh language, technical considerations in collecting the transcribed aud…

This article is devoted to solving the problem of converting sign language into a consistent text with intonation markup for subsequent voice synthesis of sign phrases by speech with intonation. The paper proposes an improved method of continuous recognition …

We compare using a PHOIBLE-based phone mapping method and using phonological features input in transfer learning for TTS in low-resource languages. We use diverse source languages (English, Finnish, Hindi, Japanese, and Russian) and target languages (Bulgaria…

This work aims to build a multilingual text-to-speech (TTS) synthesis system for ten lower-resourced Turkic languages: Azerbaijani, Bashkir, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Turkmen, Uyghur, and Uzbek. We specifically target the zero-shot learning scena…

Machine translation is an important research field in natural language processing and artificial intelligence, which studies how to use computers to automatically convert languages. We experimented with attentional neural network machine translation for Chine…

This article provides research and development of an extractive question answering system based on the BERT-like model for the Kazakh language. Developing an extractive question answering system requires large training datasets - tens of thousands of annotate…

In this study, we developed a model for automatic recognition of Kazakh speech by fine-tuning the XLSR-Wav2Vec2 pre-trained model to a corpus of Kazakh speech. Our results show that fine-tuning the wav2vec2 model on a small corpus of Kazakh speech allows a si…

With the improvement of intelligent systems, speech recognition technologies are being widely integrated into various aspects of human life. Speech recognition is applied to smart assistants, smart home infrastructure, the call center applications of banks, i…

The development of the machine translation field was driven by people’s need to communicate with each other globally by automatically translating words, sentences, and texts from one language into another. The neural machine translation approach has become on…

This paper investigates the effectiveness of transfer learning in building automatic speech recognition models for nine Turkic languages (Azerbaijani, Bashkir, Chuvash, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek), by leveraging large-scale training data…

The primary aim of this study was to contribute to the development of multilingual automatic speech recognition for lower-resourced Turkic languages. Ten languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek—were co…

Building a good speech recognition system usually requires a lot of pairing data, which poses a big challenge for low-resource languages, such as Kazakh. In recent years, unsupervised pre-training has achieved good performance in low-resource speech recogniti…

With the emergence of deep learning, the performance of automatic speech recognition (ASR) systems has remarkably improved. Especially for resource-rich languages such as English and Chinese, commercial usage has been made feasible in a wide range of applicat…

Pre-trained language models are trained on large-scale unsupervised data, and they can fine-turn the model only on small-scale labeled datasets, and achieve good results. Multilingual pre-trained language models can be trained on multiple languages, and the m…

The task of determining the similarity of text documents has received considerable attention in many areas such as Information Retrieval, Text Mining, Natural Language Processing (NLP) and Computational Linguistics. Transferring data to numeric vectors is a c…

This paper presents our systems and experimental analyses for the OpenASR21 Challenge. We describe the systems in the constrained condition, constrained-plus condition, and unconstrained condition, and our post-evaluation analyses for the Challenge. The syste…

We present the first industrial-scale open-source Kazakh speech corpus for automatic speech recognition research and development. Our corpus subsumes two previously presented corpora: 1) Kazakh speech corpus (KSC) and 2) Kazakh text-to-speech 2 (KazakhTTS2). …

We propose a two-stage approach for training a single NMT model to translate unseen languages both to and from English. For the first stage, we initialize an encoder-decoder model to pretrained XLM-R and RoBERTa weights, then perform multilingual fine-tuning …

The problems of machine translation are constantly arising. While the most advanced translation platforms, such as Google and Yandex, allow for high-quality translations of languages with simple grammatical structures, more morphologically rich languages stil…

Nowadays, due to the transition to digital data storage, there is a need to implement handwritten text recognition (HTR), which is an automatic translation of handwritten characters into a machine format. Handwriting recognition is complicated by the fact tha…

Numerous recent work on unsupervised machine translation (UMT) implies that competent unsupervised translations of low-resource and unrelated languages, such as Nepali or Sinhala, are only possible if the model is trained in a massive multilingual environment…

Wikipedia is one of the richest knowledge sources on the Web today. In order to facilitate navigating, searching, and maintaining its content, Wikipedia's guidelines state that all articles should be annotated with a so-called short description indicating the…

Today, the Transformer model, which allows parallelization and also has its own internal attention, has been widely used in the field of speech recognition. The great advantage of this architecture is the fast learning speed, and the lack of sequential operat…

The emotional speech recognition method presented in this article was applied to recognize the emotions of students during online exams in distance learning due to COVID-19. The purpose of this method is to recognize emotions in spoken speech through the know…

Ensuring the best quality and performance of modern speech technologies, today, is possible based on the widespread use of machine learning methods. The idea of this project is to study and implement an end-to-end system of automatic speech recognition using …

We present an expanded version of our previously released Kazakh text-to-speech (KazakhTTS) synthesis corpus. In the new KazakhTTS2 corpus, the overall size has increased from 93 hours to 271 hours, the number of speakers has risen from two to five (three fem…

We present the development of a dataset for Kazakh named entity recognition. The dataset was built as there is a clear need for publicly available annotated corpora in Kazakh, as well as annotation guidelines containing straightforward--but rigorous--rules an…

Applied intelligent systems play an important role in the modern world. One of their tasks is machine translation (MT) from one language into another one. MT allows people to freely communicate despite language barriers. This new technology is a special step …

In this paper we introduce the FooDI-ML dataset. This dataset contains over 1.5M unique images and over 9.5M store names, product names descriptions, and collection sections gathered from the Glovo application. The data made available corresponds to food, dri…

Despite the transition to digital information exchange, many documents, such as invoices, taxes, memos and questionnaires, historical data, and answers to exam questions, still require handwritten inputs. In this regard, there is a need to implement Handwritt…

We study training a single end-to-end (E2E) automatic speech recognition (ASR) model for three languages used in Kazakhstan: Kazakh, Russian, and English. We first describe the development of multilingual E2E ASR based on Transformer networks and then perform…

Mobile devices are transforming the way people interact with computers, and speech interfaces to applications are ever more important. Automatic Speech Recognition systems recently published are very accurate, but often require powerful machinery (specialised…

For Uyghur, Kazakh and other minority languages or dialects, it is difficult to collect large-scale labeled corpus. In the case of low resources, reducing the recognition granularity which using phonemes or characters as the recognition unit can get good char…

Automatic speech recognition is a rapidly developing area in machine learning. The most popular speech recognition systems today are end-to-end systems, especially those models that directly output a sequence of words taking into account the input sound in re…

Machine learning is one of the main branches of artificial intelligence. Its main idea is not only to use an algorithm written by a computer, but also to learn how to solve a problem on your own. Recently, in the field of translation, the issue of using machi…

This paper introduces a high-quality open-source speech synthesis dataset for Kazakh, a low-resource language spoken by over 13 million people worldwide. The dataset consists of about 93 hours of transcribed audio recordings spoken by two professional speaker…

We present a simple but effective approach for leveraging Wikipedia for neural machine translation as well as cross-lingual tasks of image captioning and dependency parsing without using any direct supervision from external parallel data or supervised models …

We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of most of the world'…

This paper evaluates the performance of several modern subword segmentation methods in a low-resource neural machine translation setting. We compare segmentations produced by applying BPE at the token or sentence level with morphologically-based segmentations…

This paper introduces the design and construction process of a bilingual machine translation auxiliary tool between Chinese and Kazakh languages. The tool uses the Jieba word segmentation tool to segment the input sentence, and then translates it according to…

Machine translation is the technology of consecutive translation of texts from one language to another by a computer program. As a result of machine translation, there are always certain disadvantages that can be solved by post-editing. Post-editing-human pro…

This article discusses the problem of handwriting recognition in Kazakh and Russian languages. This area is poorly studied since in the literature there are almost no works in this direction. We have tried to describe various approaches and achievements of re…

In this paper a hybrid example based machine translation system between Kazakh and Turkish languages is presented. The system mainly based on example based machine translation method which is supported by a statistical language model for the target language. …

The basis of word culture is the language norm. Speech culture is " the degree of reproduction, maturation of language techniques. In addition, he has not only kindness, literacy, but also the skills of accurate and correct application of language techniques,…

Unsupervised translation has reached impressive performance on resource-rich language pairs such as English-French and English-German. However, early studies have shown that in more realistic settings involving low-resource, rare languages, unsupervised trans…

We present an open-source speech corpus for the Kazakh language. The Kazakh speech corpus (KSC) contains around 332 hours of transcribed audio comprising over 153,000 utterances spoken by participants from different regions and age groups, as well as both gen…

This research approaches the task of handwritten text with attention encoder-decoder networks that are trained on Kazakh and Russian language. We developed a novel deep neural network model based on Fully Gated CNN, supported by Multiple bidirectional GRU and…

We present several neural networks to address the task of named entity recognition for morphologically complex languages (MCL). Kazakh is a morphologically complex language in which each root/stem can produce hundreds or thousands of variant word forms. This …

In this paper, we present a new Russian and Kazakh database (with about 95% of Russian and 5% of Kazakh words/sentences respectively) for offline handwriting recognition. A few pre-processing and segmentation procedures have been developed together with the d…

This paper describes characteristics which affect the sentiment analysis in the Kazakh language texts, models of morphological rules and morphological analysis algorithms, formal models of simple sentence structures in the Kazakh-Turkish combination, models a…

Grammatology is traditionally a field of linguistics that establishes and studies the relationship between the letters of the alphabet and the sounds of speech. Grammatology as a branch of linguistics appeared long ago, almost simultaneously with linguistics.…

There has been an increasing interest in learning cross-lingual word embeddings to transfer knowledge obtained from a resource-rich language, such as English, to lower-resource languages for which annotated data is scarce, such as Turkish, Russian, and many o…

In this article, we have implemented a system of multimodal recognition of Kazakh speech, based on speech and lip recognition. During the feature extraction phase, several methods have been used, such as voice activity detection (VAD), mel-frequency cepstral …

ABSTRACT The paper proposes a solution to the problem of unknown words for neural machine translation (NMT). The proposed solution is shown by the example of NMT of the Kazakh-English language pair. The novelty of the proposed technology for solving the probl…

Development of Automatic Speech Recognition system for Kazakh language is very challenging due to a lack of data.Existing data of kazakh speech with its corresponding transcriptions are heavily accessed and not enough to gain a worth mentioning results.For th…

Abstract Dictionaries play an important role in neural machine translation (NMT). However, a large dictionary requires a significant amount of memory, which limits the application of NMT and can cause a memory error. This limitation can be solved by segmentin…

This paper presents the systems submitted by the University of Groningen to the English– Kazakh language pair (both translation directions) for the WMT 2019 news translation task. We explore the potential benefits of (i) morphological segmentation (both unsup…

This paper presents the NICT’s participation in the WMT19 unsupervised news translation task. We participated in the unsupervised translation direction: German-Czech. Our primary submission to the task is the result of a simple combination of our unsupervised…

In this paper, we describe our supervised neural machine translation (NMT) systems that we developed for the news translation task for Kazakh↔English, Gujarati↔English, Chinese↔English, and English→Finnish translation directions. We focused on leveraging mult…

In this article, we describe the TALP-UPC research group participation in the WMT19 news translation shared task for Kazakh-English. Given the low amount of parallel training data, we resort to using Russian as pivot language, training subword-based statistic…

This paper describes the neural machine translation systems developed at the RWTH Aachen University for the German-English, Chinese-English and Kazakh-English news translation tasks of the Fourth Conference on Machine Translation (WMT19). For all tasks, the f…

Common intermediate language representation in neural machine translation can be used to extend bilingual to multilingual systems by incremental training. In this paper, we propose a new architecture based on introducing an interlingual loss as an additional …

Effective presentation skills can help to succeed in business, career and academy. This paper presents the design of speech assessment during the oral presentation and the algorithm for speech evaluation based on criteria of optimal intonation. As the pace of…

Word alignment play an important role in the training of statistical machine translation systems. We present a technique to refine word alignments at phrase level after the collection of sentences from the Kazakh-English parallel corpora. The estimation techn…

This paper describes the method of recognition of Kazakh vowels at the beginning of the words using Dynamic Time Warping algorithm. This can be used for acceleration of recognition since word’s first sound identification can significantly decrease the list of…

This study presents a novel translation framework by combining transfer learning and part-of-speech (POS) tagging methods to improve the performance of low-resource neural machine translation models using Kazakh-English and Turkish-English language pairs. It …

We describe the neural machine translation (NMT) system developed at the National Research Council of Canada (NRC) for the Kazakh-English news translation task of the Fourth Conference on Machine Translation (WMT19). Our submission is a multi-source NMT takin…

The lack of big parallel data is present for the Kazakh language. This problem seriously impairs the quality of machine translation from and into Kazakh. This article considers the neural machine translation of the Kazakh language on the basis of synthetic co…

This paper describes the University of Maryland’s submission to the WMT 2019 Kazakh-English news translation task. We study the impact of transfer learning from another low-resource but related language. We experiment with different ways of encoding lexical u…

We describe an evaluation of several open-source models under identical inference conditions without task-specific training. Despite covering a wide range of available models, including both multilingual systems and models specifically designed for Russian– K…

This paper describes the two submissions of Universitat d’Alacant to the English-to-Kazakh news translation task at WMT 2019. Our submissions take advantage of monolingual data and parallel data from other language pairs by means of iterative backtranslation,…

We conducted a systematic evaluation of seven large language models (LLMs) on tasks in Kazakh, a Turkic language spoken by approximately 13 million native speakers in Kazakhstan and abroad. We used six datasets corresponding to different tasks – questions ans…

—In recent years, the progress made in neural models trained on extensive multilingual text or speech data has shown great potential for improving the status of underresourced languages. This paper focuses on experimenting with three state-of-the-art speech r…

This article describes the methods of creating a system of recognizing the continuous speech of Kazakh language. Studies on recognition of Kazakh speech in comparison with other languages began relatively recently, that is after obtaining independence of the …

Automatic processing of morphologically rich, agglutinative, and low-resource languages remains challenging because productive affixation increases lexical sparsity, weakens statistical generalization, and often produces inconsistent predictions across relate…