Song Generation

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 17

All topics

GrainSpeech: Less Context, More Detail for Compact Speech Synthesis
Sep 16, 2026Zitao Liang, Chang GaoSong Generation
Department of Microelectronics, Delft University of Technology, The Netherlands
SongCraft: Unified Song Generation and Editing with Reconstructive Learning
Sep 14, 2026Haohe Liu, Varun Nagaraja, Gael Le Lan +5Song Generation
Meta AI
DiffSynth-Music: Audio-Conditioned KV-Cache Adapters for Controllable Music Generation
Sep 14, 2026Zhongjie Duan, Shengchuan Gao, Hong Zhang +1Song Generation Audio Editing
Alibaba Group · Shanghai Jiao Tong University
Cross-cultural evaluation of taste-sound correspondences in AI-generated music
Aug 4, 2026Matteo Spanio, Massimiliano Zampini, Luisa Torri +5Cross-Cultural Variation Song Generation
University of Padova, Padova, Italy · University of Trento, Trento, Italy · University of Gastronomic Sciences, Pollenzo, Italy +2
Pushing the Frontier of Full-Song Generation: Hierarchical Autoregressive Planning Meets Flow-Matching Rendering
Jul 22, 2026Junyu Dai, Xinyue Fan, Weiqin Li +14Song Generation Melody
Alibaba Token Foundry
Low-Latency Neural Models for Real-Time Music Enhancement
Jul 14, 2026Emmanouil Karystinaios, Jonathan Greif, David Nadrchal +2Speech Enhancement Song Generation
Institute of Computational Perception, Johannes Kepler University Linz, Austria
LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training
Jun 29, 2026Shun Lei, Huaicheng Zhang, Dapeng Wu +8Song Generation Text-To-Music
Tsinghua-CUHK Joint Research Center for Media Sciences, Technologies and Systems, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Wuhan University, Wuhan, China · Hong Kong Polytechnic University, Hong Kong, China +1
Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation
Jun 23, 2026Baisen Wang, Chenxi Bao, Qisong HanGenerative Music Song Generation
Work done in ZhuoLab. · DynamiX · Cardiff University
TuneJury: An Open Metric for Improving Music Generation Preference Alignment
Jun 15, 2026Yonghyun Kim, Junwon Lee, Haiwen Xia +5Text-To-Music Song Generation
Georgia Tech · KAIST · Peking University +3
Towards Unified Song Generation and Singing Voice Conversion with Accompaniment Co-Generation
Jun 5, 2026Ziyu Zhang, Chunyu Qiang, Xiaopeng Wang +10Singing Voice Conversion Song Generation
Kuaishou Technology, China · Beijing Institute of Technology, China · Institute of Automation, Chinese Academy of Sciences, China
SketchSong: Hierarchical Song Generation with Sketch Planning and Fine-Grained Multi-Track Modeling
Jun 2, 2026Xiaoyue Duan, Nanxing Hu, Yutang Feng +4Song Generation Sketches
Pattern Recognition Center, WeChat AI, Tencent Inc.
SegTune: Structured and Fine-Grained Control for Song Generation
May 31, 2026Yuejiao Wang, Zihao Ji, Pengfei Cai +6Song Generation Synthesis
Kling Team, Kuaishou Technology · University of Science and Technology of China, Hefei, Anhui, China · Peking University, Beijing, China
Live Music Diffusion Models: Efficient Fine-Tuning and Post-Training of Interactive Diffusion Music Generators
May 21, 2026Zachary Novack, Stephen Brade, Haven Kim +8Song Generation Accompaniment
UC San Diego · MIT · Adobe
APEX: Large-scale Multi-task Aesthetic-Informed Popularity Prediction for AI-Generated Music
May 5, 2026Jaavid Aktar Husain, Dorien HerremansSong Generation Aesthetics
AMAAI Lab, Singapore University of Technology and Design
Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation
May 3, 2026Jiafeng Liu, Yuanliang Dong, Hongjia Liu +8Song Generation
1Central Conservatory of Music · 2Tsinghua University
SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessment
Apr 16, 2026Dapeng Wu, Shun Lei, Wei Tan +5Song Generation Seed-Tts-Eval Benchmark
Shenzhen International Graduate School, Tsinghua University, Shenzhen, China · Tencent
HeartMuLa: A Family of Open Sourced Music Foundation Models
Jan 15, 2026Dongchao Yang, Yuxin Xie, Yuguo Yin +26Song Generation

Sep 16, 2026, eess.ASJ/K move · Enter open · S save

GrainSpeech: Less Context, More Detail for Compact Speech Synthesis

Zitao Liang, Chang Gao

Department of Microelectronics, Delft University of Technology, The Netherlands

Song Generation

Open paper AskPDF arXiv

Compact acoustic models face a challenging quality-capacity trade-off. We investigate two factors in this regime: encoder context and Mel-spectrogram supervision. A receptive-field-scaling study shows that expanding self-attention beyond 15 phonemes provides no consistent gains in pitch, energy, or duration prediction. Guided by this finding, we introduce a fixed-receptive-field convolutional encoder that reduces the respective prediction errors by 36.0%, 17.3%, and 3.4%. We further show that directly transferring image-domain gradient-variance supervision restores fine-scale variation but degrades predicted quality, motivating a Mel-specific formulation with axis-specific gradients, overlapping local statistics, and log-domain variance matching. GrainSpeech contains only 264.8K parameters and achieves 17.9x real-time Mel generation on a microcontroller (MCU), while attaining UTMOS scores comparable to substantially larger models with less than 1.5% of their parameters. Source code and demos are available at https://github.com/lab-emi/GrainSpeech.

Momentum

Related topics

Latest papers 17