2024:Music Audio Generation - Revision history

A43992899: /* Rules */

2024-10-12T03:31:50Z

‎Rules

2024-10-12T03:29:02Z

‎Metrics

2024-10-12T03:27:32Z

‎Download

2024-10-12T03:26:23Z

‎Description of Split

2024-10-12T03:25:11Z

‎Description

2024-10-12T03:25:01Z

‎Dataset

2024-10-12T03:20:17Z

‎Baseline

2024-10-12T03:19:44Z

‎Description of Split

2024-10-12T03:19:19Z

‎Description of Audio Files

2024-10-12T03:19:04Z

‎Description

@@ Line 53: / Line 53: @@
 == Rules ==
-Participants are allowed to utilize external datasets and pre-trained models to develop their systems. However, the use of the MusicGen2024 evaluation split for training or validation is strictly prohibited. Participants must ensure that their submissions are original and do not overlap with the evaluation data.
+Participants are allowed to utilize external datasets and pre-trained models to develop their systems. However, Participants should not use any test-split data from any open-source dataset for training or validation.
 == Submission ==

@@ Line 41: / Line 41: @@
 The evaluation of the generated music will be based on a combination of objective and subjective metrics:
 * '''Inception Score (IS)''': An objective metric that evaluates the diversity and quality of the generated music, based on a pre-trained music classification model.
 * '''FAD (Fréchet Audio Distance)''': Measures the similarity between the distribution of generated music and real music, capturing both quality and diversity.
-* '''Prompt Adherence Score''': A metric designed to assess how well the generated music aligns with the provided textual prompts.
+* '''CLAP-Score''': A metric designed to assess how well the generated music aligns with the provided textual prompts.
-Each metric will contribute to the final ranking, with MOS and Prompt Adherence Score being given the highest weight.
+Each metric will contribute to the final ranking.
 == Download ==

@@ Line 50: / Line 50: @@
 == Download ==
-The MusicGen2024 dataset, including both the audio clips and corresponding textual prompts, will be made available for download. Participants can access the dataset via a link that will be posted here.
+We do not provide the download of the dataset for now.
 == Rules ==

← Older revision		Revision as of 03:26, 12 October 2024
Line 27:		Line 27:

	The MirexGen2024 dataset is only used for testing.		The MirexGen2024 dataset is only used for testing.
		+	For training, any non-test-set data from the open-source world can be used.

	== Baseline ==		== Baseline ==

@@ Line 15: / Line 15: @@
 * '''Audio Clips''': A collection of diverse music clips across various genres, ranging from classical to electronic music, to help in training and evaluation.
 * '''Textual Prompts''': Detailed prompts associated with each music clip, describing the desired musical characteristics such as mood, genre, instrumentation, and tempo.
 === Description of Audio Files ===

@@ Line 9: / Line 9: @@
 === Description ===
-An in-house music generation dataset, MirexGen2024 dataset will serve as the evaluation benchmark for this task. This dataset is specially curated to facilitate the generation of music in response to specific prompts. It includes:
+For training, any non-test-set data from the open-source world can be used.
 * '''Audio Clips''': A collection of diverse music clips across various genres, ranging from classical to electronic music, to help in training and evaluation.
 * '''Textual Prompts''': Detailed prompts associated with each music clip, describing the desired musical characteristics such as mood, genre, instrumentation, and tempo.
 === Description of Audio Files ===

@@ Line 34: / Line 34: @@
 MusicGen, developed by Meta, is a single-stage transformer-based Language Model (LM) designed for conditional music generation. It operates over multiple streams of compressed discrete music tokens, eliminating the need for multi-stage models like hierarchical or upsampling methods. MusicGen efficiently generates high-quality mono and stereo music samples conditioned on text descriptions or melodic features, providing enhanced control over the output. Extensive evaluations, including both automatic and human studies, demonstrate that MusicGen outperforms baseline models in text-to-music generation benchmarks. Ablation studies further highlight the significance of its key components.
-MusicGen-large and MusicGen-medium will be used as baselines.
+(MusicGen-large)[https://huggingface.co/facebook/musicgen-large] and (MusicGen-medium)[https://huggingface.co/facebook/musicgen-medium] will be used as baselines.
 == Metrics ==

@@ Line 26: / Line 26: @@
 === Description of Split ===
-The MusicGen2024 dataset is only used for testing.
+The MirexGen2024 dataset is only used for testing.
 == Baseline ==

@@ Line 18: / Line 18: @@
 === Description of Audio Files ===
-The audio files in the MirexMusicGen2024 dataset are selected to represent a broad spectrum of musical genres and styles. Each clip is provided in a high-quality format, ensuring that the nuances of musical elements are preserved. The dataset includes clips of varying lengths, with a focus on short to medium-length excerpts (10 to 30 seconds).
+The audio files in the MirexGen2024 dataset are selected to represent a broad spectrum of musical genres and styles. Each clip is provided in a high-quality format, ensuring that the nuances of musical elements are preserved. The dataset includes clips of varying lengths, with a focus on short to medium-length excerpts (10 to 30 seconds).
 === Description of Text ===