Speech Recognition and Synthesis Models and Platforms for the Kazakh Language

Aidana Karibayeva, Vladislav Karyukin, Balzhan Abduali, Dina Amirova

Information, 2025

Full text Open access: Gold Metadata (CSL-JSON)
DOI 10.3390/info16100879
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

With the rapid development of artificial intelligence and machine learning technologies, automatic speech recognition (ASR) and Text-to-Speech (TTS) are becoming key components of the digital transformation of society. The Kazakh language, a representative of the Turkic language family, is a low-resource language. The analysis shows significant limitations in the availability of key components of the language infrastructure, namely audio corpora, language models, and high-quality speech synthesis systems. However, for the Kazakh language, which has unique phonetic, morphological, and syntactic features, the level of development of ASR/TTS technologies still lags significantly behind their counterparts for widely spoken languages. This study aims to comprehensively analyze existing speech recognition and text-to-speech models and platforms, emphasizing their applicability and adaptation to the Kazakh language. Particular attention is paid to the linguistic and technical barriers that hinder the effective integration of the Kazakh language into modern voice technologies, including the agglutinative structure, rich vowel system, and phonemic variability. This study aims to comprehensively evaluate a diverse range of existing Speech-to-Text (STT) and TTS models and platforms in terms of their applicability to the Kazakh language. We have tested both open and commercial solutions, including Whisper, GPT-4 Transcribe, ElevenLabs, OpenAI TTS, Voiser, KazakhTTS2, TurkicTTS, and others. The assessment of speech recognition was based on the WER, TER, chrF, BLEU, and COMET metrics. In contrast, speech synthesis was evaluated using MCD, PESQ, STOI, and DNSMOS, which cover both lexical-semantic and acoustic-perceptual characteristics. Based on the analysis, it has selected the most accurate universal STT system model, not trained on local data, which demonstrated high accuracy and semantic proximity. In the field, we have identified a model that combines minimal spectral distortions with high subjective sound quality.