Comparative Analysis of Models for Neural Machine Speech-to-Text Translation for Turkic State Languages

被引：0

作者：

Nurmaganbet, Dauren ^{[1
]}

Tukeyev, Ualsher ^{[1
]}

Shormakova, Assem ^{[1
]}

Zhumanov, Zhandos ^{[1
]}

机构：

[1] Al Farabi Kazakh Natl Univ, Alma Ata, Kazakhstan

来源：

INTELLIGENT INFORMATION AND DATABASE SYSTEMS, PT II, ACIIDS 2024 | 2024年 / 14796卷

关键词：

Comparative analysis; Speech-to-text; Translation; Turkic state languages;

D O I：

10.1007/978-981-97-4985-0_28

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this work, we compare and evaluate speech recognition models for the Turkic state languages, namely Azerbaijani, Kazakh, Kyrgyz, Turkish, Turkmen, and Uzbek. For this purpose, experimental studies of neural speech recognition are being conducted for three available open-source models: Whisper is an ASR system by OpenAI, TurkicASR of ISSAI, and The Massively Multilingual Speech (MMS) project of Facebook AI's initiative. This project represents a key step towards streamlining the process of recording and processing meeting minutes in diverse Turkic languages. The scientific contribution of this article is the comparative analysis and selection of speech recognition models for the Turkic state languages based on ongoing experimental studies.

引用

页码：360 / 371

页数：12

共 22 条

[1] A Deep Convolutional Neural Network-Based Speech-to-Text Conversion for Multilingual Languages
Venkatasubramanian, S.
Mohankumar, R.
COMPUTATIONAL VISION AND BIO-INSPIRED COMPUTING ( ICCVBIC 2021), 2022, 1420 : 617 - 633
[2] Establishing a Baseline of Romanian Speech-to-Text Models
Ungureanu, Dan
Badeanu, Madalina
Marica, Gabriela-Catalina
Dascalu, Mihai
Tufis, Dan Ioan
2021 INTERNATIONAL CONFERENCE ON SPEECH TECHNOLOGY AND HUMAN-COMPUTER DIALOGUE (SPED), 2021, : 132 - 138
[3] A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems
Boito, Marcely Zanon
Besacier, Laurent
Tomashenko, Natalia
Esteve, Yannick
INTERSPEECH 2022, 2022, : 1278 - 1282
[4] A COMPARATIVE ANALYSIS OF THE NOUN OF ACTION ENDING IN -ISH IN THE MODERN TURKIC LANGUAGES
Meshadiyeva, Aynel Enver Kyzy
AD ALTA-JOURNAL OF INTERDISCIPLINARY RESEARCH, 2021, 11 (01): : 98 - 101
[5] Use of Speech-to-Text Translation Resources to Address Communication Barriers in Patients With Hearing Loss: A Systematic Review
Ferraro, Tatiana
Samaha, Nadia L.
Tannan, Utkarsh
Sookram, Sebastian
Wong, Kevin
Hwa, Tiffany Peng
OTOLOGY & NEUROTOLOGY, 2024, 45 (09) : 961 - 970
[6] Novel Defense Method against Audio Adversarial Example for Speech-to-Text Transcription Neural Networks
Tamura, Keiichi
Omagari, Akitada
Hashida, Shuichi
2019 IEEE 11TH INTERNATIONAL WORKSHOP ON COMPUTATIONAL INTELLIGENCE AND APPLICATIONS (IWCIA 2019), 2019, : 115 - 120
[7] Speech-to-text Recognition for the Creation of Subtitles in Basque: An Analysis of ADITU Based on the NER Model
Tamayo, Ana
Ros-Abaurrea, Alejandro
JOURNAL OF SPECIALISED TRANSLATION, 2024, (41) : 48 - 73
[8] Comparative Study of Text-to-Speech Synthesis Techniques for Mobile Linguistic Translation Process
Chomwihoke, Phanchita
Phankokkruad, Manop
2014 IEEE INTERNATIONAL CONFERENCE ON CONTROL SYSTEM COMPUTING AND ENGINEERING, 2014, : 449 - 454
[9] Comparative analysis of the formation and translation of the terminology of fauna and flora in the Portuguese and Italian languages
Martins, Sabrina de Cassia
CONFLUENZE-RIVISTA DI STUDI IBEROAMERICANI, 2018, 10 (01): : 296 - 312
[10] On CNN Applied to Speech-to-Text-Comparative Analysis of Different Gradient Based Optimizers
Gaiceanu, Theodora
Pastravanu, Octavian
IEEE 15TH INTERNATIONAL SYMPOSIUM ON APPLIED COMPUTATIONAL INTELLIGENCE AND INFORMATICS (SACI 2021), 2021, : 85 - 90

← 1 2 3 →