Horizon Team, Xiaomi MiLM Plus

mispeech's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

jiahaomei 

authored 7 papers about 14 hours ago

EMID: An Emotional Aligned Dataset in Audio-Visual Modality

Paper • 2308.07622 • Published Aug 15, 2023 • 1

WritingBench: A Comprehensive Benchmark for Generative Writing

Paper • 2503.05244 • Published Mar 7, 2025 • 22

MM-StoryAgent: Immersive Narrated Storybook Video Generation with a Multi-Agent Paradigm across Text, Image and Audio

Paper • 2503.05242 • Published Mar 7, 2025 • 1

LARA-Gen: Enabling Continuous Emotion Control for Music Generation Models via Latent Affective Representation Alignment

Paper • 2510.05875 • Published Oct 7, 2025

DashengTokenizer: One layer is enough for unified audio understanding and generation

Paper • 2602.23765 • Published Feb 27

Dasheng AudioGen: A Unified Model for Generating Coherent Audio Scenes from Text

Paper • 2605.27838 • Published May 27

UniFlow-Audio: Unified Flow Matching for Audio Generation from Omni-Modalities

Paper • 2509.24391 • Published Sep 29, 2025

jiahaomei 

updated a Space 5 days ago

Running

Agents

6

Dasheng AudioGen Demo Has Moved

🔊

6

Dasheng AudioGen demo has moved to a new Space.

jiahaomei 

updated a model about 2 months ago

mispeech/Dasheng-AudioGen

Text-to-Audio • 2B • Updated Jun 16 • 434 • 14

richermans 

updated a collection 2 months ago

DashengAudioGen

Collection

Audio scene generators for Text-to-Speech + Text-to-Music + Text-to-Sound,, • 2 items • Updated Jun 1

jiahaomei 

updated a model 2 months ago

mispeech/Dasheng-AudioGen-Multilingual

Text-to-Audio • 2B • Updated May 28 • 41 • 6

richermans 

updated a model 2 months ago

mispeech/Dasheng-AudioGen

Text-to-Audio • 2B • Updated Jun 16 • 434 • 14

jiahaomei 

published 2 models 2 months ago

mispeech/Dasheng-AudioGen-Multilingual

Text-to-Audio • 2B • Updated May 28 • 41 • 6

mispeech/Dasheng-AudioGen

Text-to-Audio • 2B • Updated Jun 16 • 434 • 14

richermans 

updated a model 2 months ago

mispeech/Dasheng-AudioGen-Multilingual

Text-to-Audio • 2B • Updated May 28 • 41 • 6

n121854029 

updated 2 datasets 3 months ago

mispeech/MECAT-QA

Viewer • Updated May 11 • 198k • 257 • 4

mispeech/MECAT-Caption

Viewer • Updated May 11 • 40.1k • 230 • 4

jimbozhang 

updated a dataset 3 months ago

mispeech/speechocean762

Viewer • Updated Apr 30 • 5k • 1.62k • 28

richermans 

updated a model 3 months ago

mispeech/dasheng-denoiser

Audio-to-Audio • 0.1B • Updated Apr 21 • 695 • 15