Investigation of Automatic Speech Recognition Systems via the Multilingual Deep Neural Network Modeling Methods for a Very Low-Resource Language, Chaha

Authors: Tessfu Geteye Fantaye, Junqing Yu, Tulu Tilahun Hailu

ABSTRACT
Automatic speech recognition (ASR) is vital for very low-resource languages for mitigating the extinction trouble. Chaha is one of the low-resource languages, which suffers from the problem of resource insufficiency and some of its phonological, morphological, and orthographic features challenge the development and initiatives in the area of ASR. By considering these challenges, this study is the first endeavor, which analyzed the characteristics of the language, prepared speech corpus, and developed different ASR systems. A small 3-hour read speech corpus was prepared and transcribed. Different basic and rounded phone unit-based speech recognizers were explored using multilingual deep neural network (DNN) modeling methods. The experimental results demonstrated that all the basic phone and rounded phone unit-based multilingual models outperformed the corresponding unilingual models with the relative performance improvements of 5.47% to 19.87% and 5.74% to 16.77%, respectively. The rounded phone unit-based multilingual models outperformed the equivalent basic phone unit-based models with relative performance improvements of 0.95% to 4.98%. Overall, we discovered that multilingual DNN modeling methods are profoundly effective to develop Chaha speech recognizers. Both the basic and rounded phone acoustic units are convenient to build Chaha ASR system. However, the rounded phone unit-based models are superior in performance and faster in recognition speed over the corresponding basic phone unit-based models. Hence, the rounded phone units are the most suitable acoustic units to develop Chaha ASR systems.

Source:

Journal: Journal of Signal and Information Processing


DOI: 10.4236/jsip.2020.111001(PDF)
Paper Id: 97733 (metadata)

See also: Comments to Paper

About scirp

(SCIRP: http://www.scirp.org) is an academic publisher of open access journals. It also publishes academic books and conference proceedings. SCIRP currently has more than 200 open access journals in the areas of science, technology and medicine. Readers can download papers for free and enjoy reuse rights based on a Creative Commons license. Authors hold copyright with no restrictions. SCIRP calculates different metrics on article and journal level. Citations of published papers are shown based on Google Scholar and CrossRef. Most of our journals have been indexed by several world class databases. All papers are archived by PORTICO to guarantee their availability for centuries to come.
This entry was posted in JSIP. Bookmark the permalink.

Leave a Reply

Your email address will not be published. Required fields are marked *