Spoken language identification on 4 Indonesian local languages using deep learning

Abstract

Language identification is at the forefront of assistance in many applications, including multilingual speech systems, spoken language translation, multilingual speech recognition, and human-machine interaction via voice. The identification of indonesian local languages using spoken language identification technology has enormous potential to advance tourism potential and digital content in Indonesia. The goal of this study is to identify four Indonesian local languages: Javanese, Sundanese, Minangkabau, and Buginese, utilizing deep learning classification techniques such as artificial neural network (ANN), convolutional neural network (CNN), and long-term short memory (LSTM). The selected extraction feature for audio data extraction employs mel-frequency cepstral coefficient (MFCC). The results showed that the LSTM model had the highest accuracy for each speech duration (3 s, 10 s, and 30 s), followed by the CNN and ANN models.

Studi Pustaka: Analisis Kesulitan Belajar Prosedur Materi Teks Bahasa Indonesia terhadap Pembelajaran Bermanfaat Siswa Kelas 4 SD

“…Salah satu materi yang digunakan dalam kelas bahasa Indonesia adalah teks prosedur (Artawan, 2022;Wijonarko, 2022). Kategori teks bergenre faktual meliputi teks prosedur.…”

Image captioning to aid blind and visually impaired outdoor navigation

“…Convolutional neural network (CNN) has been widely used in captioning work [16], [17] since their popularity in dealing with computer vision problems such as classification [18]- [25] and object detection [26]- [30]. The ability of the long short-term memory (LSTM) network to learn order dependencies in sequence prediction problems in data series [31]- [36] makes it widely used for captioning tasks in generating sentence predictions. Research [37]- [40] utilizes a combination of CNN as feature extraction and LSTM to predict the output based on the order dependencies.…”