Cover Image

Towards Hallucination-Free Music: A Reinforcement Learning Preference Optimization Framework for Reliable Song Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Huaicheng, Tan, Wei, Li, Guangzheng, Zhang, Yixuan, Chen, Hangting, Lei, Shun, Yang, Chenyu, Wu, Zhiyong, Wang, Shuai, Huang, Qijun, Yu, Dong
Format:	Preprint
Published:	2025
Subjects:	Sound Artificial Intelligence Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment
by: Wu, Dapeng, et al.
Published: (2026)

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

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

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

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

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

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

Layer-wise Investigation of Large-Scale Self-Supervised Music Representation Models
by: Zhou, Yizhi, et al.
Published: (2025)

DualSpeechLM: Towards Unified Speech Understanding and Generation via Dual Speech Token Modeling with Large Language Models
by: Wang, Yuanyuan, et al.
Published: (2025)

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

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

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

WAKE: Watermarking Audio with Key Enrichment
by: Xu, Yaoxun, et al.
Published: (2025)

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

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

SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement
by: Yang, Chenyu, et al.
Published: (2025)

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

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

Continuous Target Speech Extraction: Enhancing Personalized Diarization and Extraction on Complex Recordings
by: Zhao, He, et al.
Published: (2024)

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

Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models
by: Yang, Yi, et al.
Published: (2025)

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

MPO: Multidimensional Preference Optimization for Language Model-based Text-to-Speech
by: Xia, Kangxiang, et al.
Published: (2025)

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

UniSep: Universal Target Audio Separation with Language Models at Scale
by: Wang, Yuanyuan, et al.
Published: (2025)

Music Similarity Representation Learning Focusing on Individual Instruments with Source Separation and Human Preference
by: Imamura, Takehiro, et al.
Published: (2025)

Fine-grained Preference Optimization Improves Zero-shot Text-to-Speech
by: Yao, Jixun, et al.
Published: (2025)

XMusic: Towards a Generalized and Controllable Symbolic Music Generation Framework
by: Tian, Sida, et al.
Published: (2025)

MusicRL: Aligning Music Generation to Human Preferences
by: Cideron, Geoffrey, et al.
Published: (2024)

Towards Musically Informed Evaluation of Piano Transcription Models
by: Hu, Patricia, et al.
Published: (2024)

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

ASRRL-TTS: Agile Speaker Representation Reinforcement Learning for Text-to-Speech Speaker Adaptation
by: Fu, Ruibo, et al.
Published: (2024)

Improving Controllability and Editability for Pretrained Text-to-Music Generation Models
by: Zhang, Yixiao
Published: (2024)

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

Seed-Music: A Unified Framework for High Quality and Controlled Music Generation
by: Bai, Ye, et al.
Published: (2024)

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

AUV: Teaching Audio Universal Vector Quantization with Single Nested Codebook
by: Chen, Yushen, et al.
Published: (2025)

MusicMamba: A Dual-Feature Modeling Approach for Generating Chinese Traditional Music with Modal Precision
by: Chen, Jiatao, et al.
Published: (2024)