Bulletin of Electrical Engineering and Informatics Vol. 11, No. 6, December 2022, pp. 3288~3293 ISSN: 2302-9285, DOI: 10.11591/eei.v11i6.4166  3288 Journal homepage: http://beei.org Spoken language identification on 4 Indonesian local languages using deep learning Panji Wijonarko, Amalia Zahra Department of Computer Science, Bina Nusantara University, Jakarta, Indonesia Article Info ABSTRACT Article history: Received May 30, 2022 Revised Aug 18, 2022 Accepted Aug 30, 2022 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. Keywords: Artificial neural network Convolutional neural network Deep learning Long-term short memory Spoken language identification This is an open access article under the CC BY-SA license. Corresponding Author: Panji Wijonarko Department of Computer Science, Bina Nusantara University Jakarta, 11480 Indonesia Email: panji.wijonarko@binus.ac.id 1. INTRODUCTION As an archipelagic country, Indonesia is made up of many ethnic groups. Language is one of Indonesia’s cultural treasures. According to language agency data, Indonesia constains around 718 languages ranging from Sabang to Merauke [1]. The diversity of languages within each tribe, often known as local languages, is an intriguing aspect to incorporate into information technology via spoken language identification. Spoken language identification is the process of utilizing a computer system to determinate the language of a spoken utterance [2]. Language identification refers to spoken communication that can be identified by a computer system [3]. Language identification is the process of distinguishing language from spoken speech [4]. 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. In the future, language identification research can be continual, particularly in support of multilingual automatic speech recognition (ASR). One of the uses of ASR in spoken language translation applications that is currently growing rapidly is in assisting different multilingual communication by translating the speaker's native language input and then translating it by machine into the target language (example: translating English to Bahasa Indonesia), or how a content multimedia on the internet can be directly translated into the language that we want. With many regions in Indonesia that can be visited by local and foreign tourists, voice technology is very useful for establishing communication between tourists and natives. Futhermore, there is a lot of digital multimedia content that uses Indonesian local languages as the main language and needs to be automatically translated,