CS Tea: Fadi Al-Ghawanmeh presents "How can machine translation help generate Arab melodic improvisation?"
Dr. Fadi Al-Ghawanmeh will speak about his research on machine translation for Arab music improvisation.
Under-resourced languages (and musics) pose a challenge to machine translation (MT). The challenge is greater when the content of the collected dataset is a varied sample taken from a data population that is even more diverse and dynamic. This is the challenge of Arab music improvisation. We present here the development of a parallel dataset consisting of vocal improvisatory sentences and their corresponding responsive instrumental responses (translations). We then proceed to experiment with machine translation to generate responsive accompaniments, comparing several translation models that differ (1) in translation approach (neural versus statistical), and (2) in the dataset handling approach (maqam-based models versus one model for all maqamat). The best translation models were also adapted to generate full instrumental improvisations by iteratively translating the translations of the most common patterns (n-grams). We outline our findings concerning these custom models and subsequently use them as a foundation to consider the future potential for large language models in music translation and background-music generation. Additionally, we delve into how they offer both opportunities and challenges for democratizing and decolonizing music generation.
Join us for coffee, tea, and conversation.
from Computer Science