A Transformer Based Pitch Sequence Autoencoder with MIDI Augmentation
Despite recent achievements of deep learning automatic music generation algorithms, few approaches have been proposed to evaluate whether a single-track music excerpt is composed by automatons or Homo sapiens. To tackle this problem, we apply a masked language model based on ALBERT for composers classification. The aim is to obtain a model that can suggest the probability a MIDI clip might be composed condition on the auto-generation hypothesis, and which is trained with only AI-composed single-track MIDI. In this paper, the amount of parameters is reduced, two methods on data augmentation are proposed as well as a refined loss function to prevent overfitting. The experiment results show our model ranks $3^{rd}$ in all the $7$ teams in the data challenge in CSMT(2020). Furthermore, this inspiring method could be spread to other music information retrieval tasks that are based on a small dataset.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationInformation RetrievalLanguage ModelingLanguage ModellingMusic GenerationMusic Information RetrievalRetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer
We introduce MIDI-VAE, a neural network model based on Variational Autoencoders that is capable of handling polyphonic music with multiple instrument tracks, as well as modeling the dynamics of music by incorporating not…
Style TransferEmotion-Guided Image to Music Generation
Generating music from images can enhance various applications, including background music for photo slideshows, social media experiences, and video creation. This paper presents an emotion-guided image-to-music generatio…
Contrastive LearningMusic GenerationEvaluating Interval-based Tokenization for Pitch Representation in Symbolic Music Analysis
Symbolic music analysis tasks are often performed by models originally developed for Natural Language Processing, such as Transformers. Such models require the input data to be represented as sequences, which is achieved…
GiantMIDI-Piano: A large-scale MIDI dataset for classical piano music
Symbolic music datasets are important for music information retrieval and musical analysis. However, there is a lack of large-scale symbolic datasets for classical piano music. In this article, we create a GiantMIDI-Pian…
Information RetrievalMusic Information RetrievalRetrievalN-Gram Unsupervised Compoundation and Feature Injection for Better Symbolic Music Understanding
The first step to apply deep learning techniques for symbolic music understanding is to transform musical pieces (mainly in MIDI format) into sequences of predefined tokens like note pitch, note velocity, and chords. Sub…