Copertina

SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Dapeng, Lei, Shun, Tan, Wei, Li, Guangzheng, Wang, Yunzhe, Zhang, Huaicheng, Zuo, Lishi, Wu, Zhiyong
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Audio and Speech Processing Artificial Intelligence Sound
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

LeVo: High-Quality Song Generation with Multi-Preference Alignment
di: Lei, Shun, et al.
Pubblicazione: (2025)

Towards Hallucination-Free Music: A Reinforcement Learning Preference Optimization Framework for Reliable Song Generation
di: Zhang, Huaicheng, et al.
Pubblicazione: (2025)

SongPrep: A Preprocessing Framework and End-to-end Model for Full-song Structure Parsing and Lyrics Transcription
di: Tan, Wei, et al.
Pubblicazione: (2025)

SongCreator: Lyrics-based Universal Song Generation
di: Lei, Shun, et al.
Pubblicazione: (2024)

SongEditor: Adapting Zero-Shot Song Generation Language Model as a Multi-Task Editor
di: Yang, Chenyu, et al.
Pubblicazione: (2024)

An End-to-End Approach for Chord-Conditioned Song Generation
di: Gao, Shuochen, et al.
Pubblicazione: (2024)

IdolSongsJp Corpus: A Multi-Singer Song Corpus in the Style of Japanese Idol Groups
di: Suda, Hitoshi, et al.
Pubblicazione: (2025)

SongTrans: An unified song transcription and alignment method for lyrics and notes
di: Wu, Siwei, et al.
Pubblicazione: (2024)

The ICASSP 2026 Automatic Song Aesthetics Evaluation Challenge
di: Ma, Guobin, et al.
Pubblicazione: (2026)

Song Aesthetics Evaluation with Multi-Stem Attention and Hierarchical Uncertainty Modeling
di: Lv, Yishan, et al.
Pubblicazione: (2026)

MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline
di: Tsai, Fang-Duo, et al.
Pubblicazione: (2026)

The THU-HCSI Multi-Speaker Multi-Lingual Few-Shot Voice Cloning System for LIMMITS'24 Challenge
di: Zhou, Yixuan, et al.
Pubblicazione: (2024)

DiffRhythm+: Controllable and Flexible Full-Length Song Generation with Preference Optimization
di: Chen, Huakang, et al.
Pubblicazione: (2025)

The Florence Price Art Song Dataset and Piano Accompaniment Generator
di: He, Tao-Tao, et al.
Pubblicazione: (2025)

Automatic Live Music Song Identification Using Multi-level Deep Sequence Similarity Learning
di: Hakala, Aapo, et al.
Pubblicazione: (2025)

SongGLM: Lyric-to-Melody Generation with 2D Alignment Encoding and Multi-Task Pre-Training
di: Yu, Jiaxing, et al.
Pubblicazione: (2024)

FruitsMusic: A Real-World Corpus of Japanese Idol-Group Songs
di: Suda, Hitoshi, et al.
Pubblicazione: (2024)

MOS-Bench: Benchmarking Generalization Abilities of Subjective Speech Quality Assessment Models
di: Huang, Wen-Chin, et al.
Pubblicazione: (2024)

UniSRM: A Unified Speech Reward Model for Reasoning-Based Fine-grained Assessment
di: Wang, Yuanyuan, et al.
Pubblicazione: (2026)

Versatile Framework for Song Generation with Prompt-based Control
di: Zhang, Yu, et al.
Pubblicazione: (2025)

MuCodec: Ultra Low-Bitrate Music Codec
di: Xu, Yaoxun, et al.
Pubblicazione: (2024)

SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition
di: Ding, Shuangrui, et al.
Pubblicazione: (2024)

TOMI: Transforming and Organizing Music Ideas for Multi-Track Compositions with Full-Song Structure
di: He, Qi, et al.
Pubblicazione: (2025)

SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing
di: Zhang, Hanlin, et al.
Pubblicazione: (2026)

AudioComposer: Towards Fine-grained Audio Generation with Natural Language Descriptions
di: Wang, Yuanyuan, et al.
Pubblicazione: (2024)

SongEval: A Benchmark Dataset for Song Aesthetics Evaluation
di: Yao, Jixun, et al.
Pubblicazione: (2025)

Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic Prompts
di: Lei, Shun, et al.
Pubblicazione: (2023)

CHORDONOMICON: A Dataset of 666,000 Songs and their Chord Progressions
di: Kantarelis, Spyridon, et al.
Pubblicazione: (2024)

Segment-Factorized Full-Song Generation on Symbolic Piano Music
di: Chen, Ping-Yi, et al.
Pubblicazione: (2025)

Hybrid-Sep: Language-queried audio source separation via pre-trained Model Fusion and Adversarial Diffusion Training
di: Feng, Jianyuan, et al.
Pubblicazione: (2025)

A Multi-Stage Framework for Multimodal Controllable Speech Synthesis
di: Niu, Rui, et al.
Pubblicazione: (2025)

The Codec Language Model-based Zero-Shot Spontaneous Style TTS System for CoVoC Challenge 2024
di: Zhou, Shuoyi, et al.
Pubblicazione: (2024)

CSL-L2M: Controllable Song-Level Lyric-to-Melody Generation Based on Conditional Transformer with Fine-Grained Lyric and Musical Controls
di: Chai, Li, et al.
Pubblicazione: (2024)

MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech
di: Chen, Huakang, et al.
Pubblicazione: (2026)

VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling
di: Zhou, Yixuan, et al.
Pubblicazione: (2024)

In This Environment, As That Speaker: A Text-Driven Framework for Multi-Attribute Speech Conversion
di: Jin, Jiawei, et al.
Pubblicazione: (2025)

SOVA-Bench: Benchmarking the Speech Conversation Ability for LLM-based Voice Assistant
di: Hou, Yixuan, et al.
Pubblicazione: (2025)

Via Score to Performance: Efficient Human-Controllable Long Song Generation with Bar-Level Symbolic Notation
di: Wang, Tongxi, et al.
Pubblicazione: (2025)

Song Data Cleansing for End-to-End Neural Singer Diarization Using Neural Analysis and Synthesis Framework
di: Munakata, Hokuto, et al.
Pubblicazione: (2024)

Improving Speech Enhancement with Multi-Metric Supervision from Learned Quality Assessment
di: Wang, Wei, et al.
Pubblicazione: (2025)