While creating a musical composition, it becomes essential to consider several acoustic aspects in modern digital music creation. Such components determine the features of the piece’s percussive aspects, like in the case of drum samples. To determine whether a specific drum sample suits the current musical context, artists must utilize their aesthetic judgment. However, the painstaking effort of choosing drum samples from a potentially extensive library could often stifle the flow of creative thought. Machine learning algorithms are being developed by researchers at the Sony Computer Science Laboratories (CSL) in France to make it simpler for music producers to locate and retrieve particular audio samples from a database. The samples in an artist’s library can be ranked according to how well they fit into different musical contexts at various points during the production process. Working on this front, Sony has unveiled SampleMatch, a machine learning-based algorithm that can automatically find drum samples from vast archives that correspond to a particular music track. The model will be presented in December at the prestigious ISMIR 2022 conference, which focuses on music information retrieval.
Since there are numerous activities in the realm of music creation where applying AI could be beneficial, Sony aims to build AI applications that could simplify the lives of music producers. One such tiresome chore is choosing a drum sample. It is the technique by which music producers look for drum samples that would complement particular drumless music tracks. Finding appropriate drum samples might take a lot of time and effort because these drum sample libraries are frequently enormous. There are currently very few simple computational tools available to music producers to help them select percussion samples. The available ones mainly involve using tags or keywords to filter big datasets.
The team has previously attempted to create a comparable method to gather drum samples more quickly and successfully. However, they could not do so previously because of the system’s complexity and technological constraints. Estimating whether two data points fit together has become simpler because of recent developments in contrastive learning and advancements in neural network encoders. As a result, the system was made more general and more straightforward to implement. Musicians can feed their track into their system at any level of creation when utilizing SampleMatch. The drum sample library is then automatically sorted by what the algorithm determines will work best with it.
A large dataset of 4,830 electronic music songs and 885 well-known pop/rock tracks was used to train SampleMatch. Although there are currently systems that use extracted musical features to match audio samples, the quality of their retrieval depends on the predefined features and the type of samples. When computing a matching score for drum samples, it is unclear which features to include. SampleMatch could be applied to different types of audio matching even though it was developed to discover which percussion samples matched a specific track. The model could be trained to extract complementary bass, guitar, or other instrumental sounds using various training sample pairings.
Sony CSL intends to extend the audio retrieval model in the future in order to help music producers find appropriate drum samples or other instrumental samples for their compositions. Additionally, a thorough examination of how the system came to organize the data could aid in developing fresh hypotheses that could direct music production activities. In more detail, the researchers’ ability to reverse-engineer the system may enable them to specify a few general guidelines that musicians should adhere to while blending their music. The team wants to use this technique in conjunction with Sony’s DrumGAN technology to produce drum samples that precisely complement a specific tune.
Khushboo Gupta is a consulting intern at MarktechPost. She is currently pursuing her B.Tech from the Indian Institute of Technology(IIT), Goa. She is passionate about the fields of Machine Learning, Natural Language Processing and Web Development. She enjoys learning more about the technical field by participating in several challenges.
See How AI is Advancing Medicine and Research