• Journal of Intelligence and Information Systems
• /
• v.27 no.2
• /
• pp.17-32
• /
• 2021

Speaker recognition is generally divided into speaker identification and speaker verification. Speaker recognition plays an important function in the automatic voice system, and the importance of speaker recognition technology is becoming more prominent as the recent development of portable devices, voice technology, and audio content fields continue to expand. Previous speaker recognition studies have been conducted with the goal of automatically determining who the speaker is based on voice files and improving accuracy. Speech is an important sociolinguistic subject, and it contains very useful information that reveals the speaker's attitude, conversation intention, and personality, and this can be an important clue to speaker recognition. The final ending used in the speaker's speech determines the type of sentence or has functions and information such as the speaker's intention, psychological attitude, or relationship to the listener. The use of the terminating ending has various probabilities depending on the characteristics of the speaker, so the type and distribution of the terminating ending of a specific unidentified speaker will be helpful in recognizing the speaker. However, there have been few studies that considered speech in the existing text-based speaker recognition, and if speech information is added to the speech signal-based speaker recognition technique, the accuracy of speaker recognition can be further improved. Hence, the purpose of this paper is to propose a novel method using speech style expressed as a sentence-final ending to improve the accuracy of Korean speaker recognition. To this end, a method called sentence sequencing that generates vector values by using the type and frequency of the sentence-final ending appearing in the utterance of a specific person is proposed. To evaluate the performance of the proposed method, learning and performance evaluation were conducted with a actual drama script. The method proposed in this study can be used as a means to improve the performance of Korean speech recognition service.

• (The) Research of the performance art and culture
• /
• no.43
• /
• pp.145-172
• /
• 2021

Shin Myung-soon's is based on the taboo 'bombing of the Han River Bridge'. The reality of the bombing of the Han River Bridge in 1950 and the shooting of Colonel Choi Chang-sik was known only as a word of mouth. At that time, the ruling class did not want to reveal the painful mistakes of the unfavorable war situation in the early days of the war and the false broadcasting of the president. The truth of the case, which was kept completely secret even to the bereaved family, could only be revealed after the regime change. After that, the bereaved family of Colonel Choi Chang-sik confirmed the innocence of the deceased through a request for retrial, and then the was born. However, the fate of was not so smooth. At the time, the performance officials vividly remember the difficulties they had with the text. Despite passing the pre-screening of the script, the performance was canceled just before the performance. The fact that the National Theater, officials from the Ministry of Culture and Education, and even military generals visited the practice room to stop the performance, on the contrary, was a testimony to the dangers of . It can be summarized as a crack in official history and a move to stop it. was later adapted into a special TV drama in 1981 and was first released to the public. This was a very meaningful step in terms of dealing with politically sensitive subjects on television, but the inconsistency of in the first place has largely disappeared. After that, in 1988, only after democracy entered the phase of appeasement, could be performed in its full form. In short, can be said to be an example of a process in which the history of the Korean War recorded from the standpoint of an established order and the counter-memory that crack it up are transformed according to the changes of the times and media.