Speech Recognition and Synthesis Models and Platforms for the Kazakh Language
Open Access
- 10 October 2025
- journal article
- research article
- Published by MDPI AG in Information
- Vol. 16 (10) , 879
Abstract
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 of the Turkic language family, remains a low-resource language with limited audio corpora, language models, and high-quality speech synthesis systems. This study provides a comprehensive analysis of existing speech recognition and synthesis models, emphasizing their applicability and adaptation to the Kazakh language. Special attention is given to linguistic and technical barriers, including the agglutinative structure, rich vowel system, and phonemic variability. Both open-source and commercial solutions were evaluated, including Whisper, GPT-4 Transcribe, ElevenLabs, OpenAI TTS, Voiser, KazakhTTS2, and TurkicTTS. Speech recognition systems were assessed using BLEU, WER, TER, chrF, and COMET, while speech synthesis was evaluated with MCD, PESQ, STOI, and DNSMOS, thus covering both lexical–semantic and acoustic–perceptual characteristics. The results demonstrate that, for speech-to-text (STT), the strongest performance was achieved by Soyle on domain-specific data (BLEU 74.93, WER 18.61), while Voiser showed balanced accuracy (WER 40.65–37.11, chrF 80.88–84.51) and GPT-4 Transcribe achieved robust semantic preservation (COMET up to 1.02). In contrast, Whisper performed weakest (WER 77.10, BLEU 13.22), requiring further adaptation for Kazakh. For text-to-speech (TTS), KazakhTTS2 delivered the most natural perceptual quality (DNSMOS 8.79–8.96), while OpenAI TTS achieved the best spectral accuracy (MCD 123.44–117.11, PESQ 1.14). TurkicTTS offered reliable intelligibility (STOI 0.15, PESQ 1.16), and ElevenLabs produced natural but less spectrally accurate speech.Keywords
All Related Versions
Funding Information
- Ministry of Science and Higher Education of the Republic of Kazakhstan (IRN AP AP23488624)
This publication has 45 references indexed in Scilit:
- Automatic Speech Recognition: A survey of deep learning techniques and approachesInternational Journal of Cognitive Computing in Engineering, 2025
- Multilingual end-to-end ASR for low-resource Turkic languages with common alphabetsScientific Reports, 2024
- Noise-Robust Multilingual Speech Recognition and the Tatar Speech Corpus2024
- Speech recognition for Kazakh language: a research paperProcedia Computer Science, 2024
- A study of transformer-based end-to-end speech recognition system for Kazakh languageScientific Reports, 2022
- Universal Programs for Stemming, Segmentation, Morphological Analysis of Turkic Words2021
- Inferring the Complete Set of Kazakh Endings as a Language Resource2020
- Morphological segmentation method for Turkic language neural machine translationCogent Engineering, 2020
- Human Aspects of IT for the Aged Population. Design for Everyday Life2015
- A state-space approach to orthogonal digital filters for VLSI implementation2003