paper-with-me

홈 › Papers

Evaluating Deep Music Generation Methods Using Data Augmentation

2021-12-31 · Toby Godwin, Georgios Rizos, Alice Baird, Najla D. Al Futaisi, Vincent Brisse, Bjoern W. Schuller

Despite advances in deep algorithmic music generation, evaluation of generated samples often relies on human evaluation, which is subjective and costly. We focus on designing a homogeneous, objective framework for evaluating samples of algorithmically generated music. Any engineered measures to evaluate generated music typically attempt to define the samples' musicality, but do not capture qualities of music such as theme or mood. We do not seek to assess the musical merit of generated music, but instead explore whether generated samples contain meaningful information pertaining to emotion or mood/theme. We achieve this by measuring the change in predictive performance of a music mood/theme classifier after augmenting its training data with generated samples. We analyse music samples generated by three models -- SampleRNN, Jukebox, and DDSP -- and employ a homogeneous framework across all methods to allow for objective comparison. This is the first attempt at augmenting a music genre classification dataset with conditionally generated music. We investigate the classification performance improvement using deep music generation and the ability of the generators to make emotional music by using an additional, emotion annotation of the dataset. Finally, we use a classifier trained on real data to evaluate the label validity of class-conditionally generated samples.

📄 PDF Abstract BibTeX arXiv:2201.00052

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationGenre classificationMusic GenerationMusic Genre Classification

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
VQ-VAE VQ-VAE is a type of variational autoencoder that uses vector quantisation to obtain a discrete latent representation. It differs from…
Residual Connection 설명 없음
Dilated Convolution 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Jukebox 설명 없음

Similar Papers 제목 키워드 기반

Evaluating Fake Music Detection Performance Under Audio Augmentations

2025-07-07 · Tomasz Sroka, Tomasz Wężowicz, Dominik Sidorczuk, Mateusz Modrzejewski arxiv

With the rapid advancement of generative audio models, distinguishing between human-composed and generated music is becoming increasingly challenging. As a response, models for detecting fake music have been proposed. In…

DeepFake Detection

Evaluating Disentangled Representations for Controllable Music Generation

2026-02-10 · Laura Ibáñez-Martínez, Chukwuemeka Nkama, Andrea Poltronieri, Xavier Serra 외 arxiv

Recent approaches in music generation rely on disentangled representations, often labeled as structure and timbre or local and global, to enable controllable synthesis. Yet the underlying properties of these embeddings r…

Music Generation

Mixing-Specific Data Augmentation Techniques for Improved Blind Violin/Piano Source Separation

2020-08-06 · Ching-Yu Chiu, Wen-Yi Hsiao, Yin-Cheng Yeh, Yi-Hsuan Yang 외

Blind music source separation has been a popular and active subject of research in both the music information retrieval and signal processing communities. To counter the lack of available multi-track data for supervised …

Data AugmentationInformation RetrievalMusic Information RetrievalMusic Source Separation+1

Incorporating Music Knowledge in Continual Dataset Augmentation for Music Generation

2020-06-23 · Alisa Liu, Alexander Fang, Gaëtan Hadjeres, Prem Seetharaman 외

Deep learning has rapidly become the state-of-the-art approach for music generation. However, training a deep model typically requires a large training set, which is often not available for specific musical styles. In th…

Music Generation

Multimodal Music Generation with Explicit Bridges and Retrieval Augmentation

2024-12-12 · Baisen Wang, Le Zhuo, Zhaokai Wang, Chenxi Bao 외

Multimodal music generation aims to produce music from diverse input modalities, including text, videos, and images. Existing methods use a common embedding space for multimodal fusion. Despite their effectiveness in oth…

cross-modal alignmentMultimodal Music GenerationMusic GenerationRetrieval