UniSinger unifies speaker-cloned song generation and accompaniment co-generation SVC in one multimodal diffusion transformer model trained with curriculum learning via task-specific modality masking.
Songeval: A benchmark dataset for song aesthetics evaluation
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
abstract
Aesthetics serve as an implicit and important criterion in song generation tasks that reflect human perception beyond objective metrics. However, evaluating the aesthetics of generated songs remains a fundamental challenge, as the appreciation of music is highly subjective. Existing evaluation metrics, such as embedding-based distances, are limited in reflecting the subjective and perceptual aspects that define musical appeal. To address this issue, we introduce SongEval, the first open-source, large-scale benchmark dataset for evaluating the aesthetics of full-length songs. SongEval includes over 2,399 songs in full length, summing up to more than 140 hours, with aesthetic ratings from 16 professional annotators with musical backgrounds. Each song is evaluated across five key dimensions: overall coherence, memorability, naturalness of vocal breathing and phrasing, clarity of song structure, and overall musicality. The dataset covers both English and Chinese songs, spanning nine mainstream genres. Moreover, to assess the effectiveness of song aesthetic evaluation, we conduct experiments using SongEval to predict aesthetic scores and demonstrate better performance than existing objective evaluation metrics in predicting human-perceived musical quality.
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
Polyphonia improves zero-shot stem-specific timbre transfer in polyphonic music by 15.5% target alignment via acoustic-informed attention calibration that uses probabilistic priors to set coarse boundaries.
MIDI-SAG generates consistent long-form singing accompaniments by feeding symbolic MIDI timing, chords, and structure labels into a compositional pipeline built from pre-trained modules.
MADB is a 9,999-track music aesthetics benchmark with multi-dimensional professional annotations revealing that current pretrained audio models capture only partial aesthetic information.
APEX jointly predicts popularity and aesthetic quality for AI-generated music from MERT embeddings and shows that aesthetic features improve human preference prediction on unseen generative systems.
SongBench is a new fine-grained benchmark for song quality assessment with seven dimensions and an expert-annotated dataset of 11,717 samples showing high correlation with professional ratings.
A zero-training VLM framework generates music from images via ABC notation, multi-modal RAG, and self-refinement while providing text and visual explanations for the outputs.
LeVo 2 presents a hierarchical LLM-Diffusion model with progressive post-training stages to generate full-length songs that balance semantic planning, track-specific acoustics, and musicality.
SketchSong uses temporal sketch planning with high-level tokens and explicit modeling of four tracks (vocals, bass, drums, other) to generate more coherent songs than baselines.
LaDA-Band generates complete vocal-aligned instrumental accompaniments with discrete masked diffusion, claiming simultaneous gains in audio fidelity, long-range coherence, and orchestration quality.
A text-to-music model is improved by conditioning on and selecting with a human preference reward, where expert iteration on top outputs contributes the largest measured gains on 100 Song Describer prompts.
citing papers explorer
-
Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation
UniSinger unifies speaker-cloned song generation and accompaniment co-generation SVC in one multimodal diffusion transformer model trained with curriculum learning via task-specific modality masking.
-
Polyphonia: Zero-Shot Timbre Transfer in Polyphonic Music with Acoustic-Informed Attention Calibration
Polyphonia improves zero-shot stem-specific timbre transfer in polyphonic music by 15.5% target alignment via acoustic-informed attention calibration that uses probabilistic priors to set coarse boundaries.
-
MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline
MIDI-SAG generates consistent long-form singing accompaniments by feeding symbolic MIDI timing, chords, and structure labels into a compositional pipeline built from pre-trained modules.
-
MADB: A Large-Scale Music Aesthetics Dataset with Professional and Multi-Dimensional Annotations
MADB is a 9,999-track music aesthetics benchmark with multi-dimensional professional annotations revealing that current pretrained audio models capture only partial aesthetic information.
-
APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music
APEX jointly predicts popularity and aesthetic quality for AI-generated music from MERT embeddings and shows that aesthetic features improve human preference prediction on unseen generative systems.
-
SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment
SongBench is a new fine-grained benchmark for song quality assessment with seven dimensions and an expert-annotated dataset of 11,717 samples showing high correlation with professional ratings.
-
Zero-Effort Image-to-Music Generation: An Interpretable RAG-based VLM Approach
A zero-training VLM framework generates music from images via ABC notation, multi-modal RAG, and self-refinement while providing text and visual explanations for the outputs.
-
LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training
LeVo 2 presents a hierarchical LLM-Diffusion model with progressive post-training stages to generate full-length songs that balance semantic planning, track-specific acoustics, and musicality.
-
SketchSong: Hierarchical Song Generation with Sketch Planning and Fine-Grained Multi-Track Modeling
SketchSong uses temporal sketch planning with high-level tokens and explicit modeling of four tracks (vocals, bass, drums, other) to generate more coherent songs than baselines.
-
LaDA-Band: Language Diffusion Models for Vocal-to-Accompaniment Generation
LaDA-Band generates complete vocal-aligned instrumental accompaniments with discrete masked diffusion, claiming simultaneous gains in audio fidelity, long-range coherence, and orchestration quality.
-
Improving Text-to-Music Generation with Human Preference Rewards
A text-to-music model is improved by conditioning on and selecting with a human preference reward, where expert iteration on top outputs contributes the largest measured gains on 100 Song Describer prompts.