PopMAG: Pop Music Accompaniment Generation

Ren, Yang; He, Jinzheng; Xu, Tao; Qin, Tao; Zhang, Zhao; Liu, Tie-Yan

doi:10.48550/arxiv.2008.07703

Cited by 2 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Music Information Retrieval (MIR) community, many researchers have made great efforts to learn effective music representation applied in different music-related tasks, such as music classification [7,8,24,27,35,37,38], cover song identification [19,[39][40][41][42], music generation [5,18,26,30,31]. However, most of them learn music representation in a supervised manner.…”

Section: Introductionmentioning

confidence: 99%

Contrastive Learning with Positive-Negative Frame Mask for Music Representation

Yao

Zhao

Zhang

et al. 2022

Proceedings of the ACM Web Conference 2022

Self Cite

View full text Add to dashboard Cite

Self-supervised learning, especially contrastive learning, has made an outstanding contribution to the development of many deep learning research fields. Recently, researchers in the acoustic signal processing field noticed its success and leveraged contrastive learning for better music representation. Typically, existing approaches maximize the similarity between two distorted audio segments sampled from the same music. In other words, they ensure a semantic agreement at the music level. However, those coarse-grained methods neglect some inessential or noisy elements at the frame level, which may be detrimental to the model to learn the effective representation of music. Towards this end, this paper proposes a novel Positive-nEgative frame mask for Music Representation based on the contrastive learning framework, abbreviated as PEMR. Concretely, PEMR incorporates a Positive-Negative Mask Generation module, which leverages transformer blocks to generate frame masks on Log-Mel spectrogram. We can generate self-augmented negative and positive samples by masking important components or inessential components, respectively. We devise a novel contrastive learning objective to accommodate both self-augmented positives/negatives sampled from the same music. We conduct experiments on four public datasets. The experimental results of two music-related downstream tasks, music classification and cover song identification, demonstrate the generalization ability and transferability of music representation learned by PEMR. CCS CONCEPTS• Computing methodologies → Unsupervised learning; Learning latent representations.

show abstract

Section: Introductionmentioning

confidence: 99%

Contrastive Learning with Positive-Negative Frame Mask for Music Representation

Yao

Zhao

Zhang

et al. 2022

Proceedings of the ACM Web Conference 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…In Music Information Retrieval (MIR) community, many researchers have made great efforts to learn effective music representation applied in different music-related tasks, such as music classification [7,8,24,28,35,37,38], cover song identification [19,[39][40][41][42], music generation [5,18,26,30,31]. However, most of them learn music representation in a supervised manner.…”

Section: Introductionmentioning

confidence: 99%

Contrastive Learning with Positive-Negative Frame Mask for Music Representation

Yao,

Zhao,

Zhang

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Self-supervised learning, especially contrastive learning, has made an outstanding contribution to the development of many deep learning research fields. Recently, researchers in the acoustic signal processing field noticed its success and leveraged contrastive learning for better music representation. Typically, existing approaches maximize the similarity between two distorted audio segments sampled from the same music. In other words, they ensure a semantic agreement at the music level. However, those coarse-grained methods neglect some inessential or noisy elements at the frame level, which may be detrimental to the model to learn the effective representation of music. Towards this end, this paper proposes a novel Positive-nEgative frame mask for Music Representation based on the contrastive learning framework, abbreviated as PEMR. Concretely, PEMR incorporates a Positive-Negative Mask Generation module, which leverages transformer blocks to generate frame masks on Log-Mel spectrogram. We can generate self-augmented negative and positive samples by masking important components or inessential components, respectively. We devise a novel contrastive learning objective to accommodate both self-augmented positives/negatives sampled from the same music. We conduct experiments on four public datasets. The experimental results of two music-related downstream tasks, music classification and cover song identification, demonstrate the generalization ability and transferability of music representation learned by PEMR 1 . CCS CONCEPTS• Computing methodologies → Unsupervised learning; Learning latent representations.

show abstract

PopMAG: Pop Music Accompaniment Generation

Cited by 2 publications

References 18 publications

Contrastive Learning with Positive-Negative Frame Mask for Music Representation

Contrastive Learning with Positive-Negative Frame Mask for Music Representation

Contrastive Learning with Positive-Negative Frame Mask for Music Representation

Contact Info

Product

Resources

About