Research Article
Korean Spoken Accent Identification Using T-vector Embeddings
Yong Su Om*,
Hak Sung Kim
Issue:
Volume 13, Issue 2, April 2025
Pages:
13-20
Received:
18 May 2025
Accepted:
12 June 2025
Published:
30 June 2025
Abstract: In this paper, we introduce a spoken accent identification system for the Korean language, which utilize t-vector embeddings extracted from state-of-the-art TitaNet neural network. To implement the Korean spoken accent identification system, we propose two approaches: First, we introduce a collection method of training data for the Korean spoken accent identification. Korean accents can be broadly classified into four categories: standard accent, southern accent, northwestern accent and northeastern accent. Generally, in Korean language, the speech data for standard accent can be easily obtained via different videos and websites, but the rest of the data except standard accent are very rare and therefore difficult to collect. To mitigate the impact of this data scarcity, we introduce a synthetic audio augmentation using Text-to-Speech (TTS) synthesis techniques. This process is done under the condition that the synthetic audio generated by TTS should be retain accent information of original speaker. Second, we propose an approach to build the deep neural network (DNN) for Korean spoken accent identification in a manner that fine-tune the trainable parameters of a pre-trained TitaNet speaker recognition model by using aforementioned training dataset. Based on the trained TitaNet model, the accent identification is performed using t-vector embedding features extracted from that model, and cosine distance function. The experimental results show that our proposed accent identification system is superior to the systems based on other state-of-the-art DNNs such as the x-vector and ECAPA-TDNN.
Abstract: In this paper, we introduce a spoken accent identification system for the Korean language, which utilize t-vector embeddings extracted from state-of-the-art TitaNet neural network. To implement the Korean spoken accent identification system, we propose two approaches: First, we introduce a collection method of training data for the Korean spoken ac...
Show More
Research Article
Impacts of Dams Construction and Water Harvesting Programs on Community Perception Red Sea in Eastern Sudan
Nawara Mohamed Mohamed,
Muna Mahjoub Mohamed*
Issue:
Volume 13, Issue 2, April 2025
Pages:
21-31
Received:
9 May 2025
Accepted:
29 May 2025
Published:
14 July 2025
Abstract: The present study aimed to investigate the effect of dams constructed for providing drinking water and for irrigation in the Red Sea state of Sudan. Water harvesting programs implemented by government with assistance of international non-governmental organization were investigated for their effectiveness. The study utilized secondary data literature and some photos of the dam. The area of study is located in the northeast of Sudan latitude 16°-22°N; longitude 35°-37°E. The primary data covered both direct questionnaire and key persons discussion. The area of study constituted about 10% of the total area of Sudan. As described by reports, the topography composed of rocky hills, mountains, outcrop rocks and a network of seasonal watercourses and streams. The hilly nature of the topography and the Basement Complex formation of the base rock made surface rain run-off the only source of fresh water. Open key person discussion pointed to the limited water supply due to geologic and climatic factors. Surface run-off is provided by seasonal stream where Khor Arba’ provides 60% of fresh drinking water, the amounts are affected by years of drought. Water distribution is controlled through a pipe network. Five major catchments were identified according to hydrological and morphological features and were important supply for rain-fed agriculture. The total annual groundwater recharge is 2.06 × 106 m3. The annual discharge through underground outflow at the ‘lower gate’ is 3.29 × 105 m3/year. Groundwater discharge due to pumping from Khor Arba’at basin is 4.38 × 106 m3/year on average. Gates were designed in the dam to reduce siltation. However, sedimentation caused pipes blockage. Results of questionnaire showed that most of the respondents at Arba’at (80%) and Sinkat (92%) were aware of the concept of water harvesting. Disiltation benefit of the dams were acknowledged at both Arba’at (61%) and Sinkat (50%), while deepening of wells was expressed by 40% at Sinkat. Water conservation activities existed at Arba’at (80%) only. Most (85%) were willing to participate in water management. Associations in respondents’ opinion were significant (P =.000) for both desalinization of dams and commitment to water conservation. The positive effects of Non-organization activities in the areas were expressed by participants in both areas. Significant (P =.000) associations could be obtained in respondent’ opinion between the two areas. Significant (P=0.00) associations between respondents’ opinion in the two areas was obtained. Also many respondents at Arba’at (98%) and Sinkat (94%) believed that traditional laws have positive effects on natural resource management.
Abstract: The present study aimed to investigate the effect of dams constructed for providing drinking water and for irrigation in the Red Sea state of Sudan. Water harvesting programs implemented by government with assistance of international non-governmental organization were investigated for their effectiveness. The study utilized secondary data literatur...
Show More
