Open AccessIdentifying the influence of transfer learning method in developing an end-to-end automatic speech recognition system with a low data level
Author(s) -
Оrken Mamyrbayev,
Keylan Alimhan,
Дина Оралбекова,
Akbayan Bekarystankyzy,
Багашар Жумажанов
Publication year - 2022
Publication title -
eastern-european journal of enterprise technologies
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.268
H-Index - 24
eISSN - 1729-4061
pISSN - 1729-3774
DOI - 10.15587/1729-4061.2022.252801
Subject(s) - computer science , agglutinative language , transfer of learning , artificial intelligence , deep learning , machine learning , natural language processing , speech recognition , morpheme
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 machine learning methods, as well as to develop new mathematical models and algorithms for solving the problem of automatic speech recognition for agglutinative (Turkic) languages.Many research papers have shown that deep learning methods make it easier to train automatic speech recognition systems that use an end-to-end approach. This method can also train an automatic speech recognition system directly, that is, without manual work with raw signals. Despite the good recognition quality, this model has some drawbacks. These disadvantages are based on the need for a large amount of data for training. This is a serious problem for low-data languages, especially Turkic languages such as Kazakh and Azerbaijani. To solve this problem, various methods are needed to apply. Some methods are used for end-to-end speech recognition of languages belonging to the group of languages of the same family (agglutinative languages). Method for low-resource languages is transfer learning, and for large resources – multi-task learning. To increase efficiency and quickly solve the problem associated with a limited resource, transfer learning was used for the end-to-end model. The transfer learning method helped to fit a model trained on the Kazakh dataset to the Azerbaijani dataset. Thereby, two language corpora were trained simultaneously. Conducted experiments with two corpora show that transfer learning can reduce the symbol error rate, phoneme error rate (PER), by 14.23 % compared to baseline models (DNN+HMM, WaveNet, and CNC+LM). Therefore, the realized model with the transfer method can be used to recognize other low-resource languages.