Pic Courtesy: ytimg
The K-pop label responsible for the sensational boy band BTS has yet again made a significant breakthrough in music by leveraging artificial intelligence to fuse the voice of a South Korean singer with native speakers from five other languages. HYBE, the largest music label in South Korea, utilized AI technology to facilitate the release of a song by the singer MIDNATT in six distinct languages.
In May, the track was launched in Korean, English, Spanish, Chinese, Japanese, and Vietnamese, regardless of the singer’s limited proficiency in these languages. Although various K-pop artists have previously released songs in English and Japanese along with their native Korean, the use of AI for a simultaneous release in six languages is a first on a global scale, as claimed by HYBE. Chung Wooyong, the head of HYBE’s interactive media, suggests that this novel technology could be employed for more prominent acts.
Despite only speaking limited English and Chinese in addition to his native Korean, MIDNATT, whose real name is Lee Hyun, managed to record the song “Masquerade” in all six languages. The lyrics were recited by native speakers and these recordings were then seamlessly integrated with MIDNATT’s vocals with the aid of HYBE’s proprietary AI music technology, as elucidated by Chung. He split a piece of sound into separate elements — pronunciation, timbre, pitch, and volume, then concentrated on pronunciation, related to tongue movement, and let the imagination guide them in determining the potential of technology.
MIDNATT reported that the utilization of AI has granted him a wider range of artistic expression. Valerio Velardo, director of The Sound of AI, a Spain-based consultancy service for AI music and audio, stated that while the technology isn’t novel, its application in music is innovative. He believes that in the long term, AI music technology will benefit not only professional musicians but also a broader audience.
The song is the latest testament to AI’s growing impact on the music industry, particularly as the Grammy Awards have recently established new rules to control AI-generated song mash-ups that are increasingly prevalent on social media.
Editorial Team