Towards Fine-Grained Multi-Dimensional Speech Understanding: Data Pipeline, Benchmark, and Model
ASLP-lab
ASLP-lab
AI & ML interests
None yet
Recent Activity
updated a dataset about 4 hours ago
ASLP-lab/SongFormBench updated a model about 4 hours ago
ASLP-lab/SongFormer updated a collection 1 day ago
FMSUOrganizations
None yet
spaces 8
Configuration error
Agents
9
YingMusic-Singer-Plus
π€
Edit lyrics, keep the melody
Runtime error
Agents
12
WenetSpeech Yue
π₯
Large-Scale Cantonese Speech Corpus
Runtime error
Agents
1
VoiceSculptor
π
Running on Zero
Agents
44
DiffRhythm2
π΅
Generate a full song from lyrics and style prompts
Configuration error
Agents
22
SongFormer
π΅
State-of-the-art music analysis with multi-scale datasets
Running on Zero
Agents
Featured
687
DiβͺβͺRhythm
πΆ
Blazingly Fast and Embarrassingly Simple Song Generation
models 35
ASLP-lab/SongFormer
0.7B β’ Updated β’ 353 β’ 17
ASLP-lab/FM-Speech
Audio Classification β’ Updated
ASLP-lab/Speaker-Reasoner
32B β’ Updated β’ 70 β’ 1
ASLP-lab/Speaker-Reasoner-4194h
32B β’ Updated β’ 76
ASLP-lab/YingMusic-Singer-Plus
Updated β’ 1.83k β’ 7
ASLP-lab/OmniCodec
Feature Extraction β’ Updated β’ 1
ASLP-lab/OSUM-Pangu
Audio-to-Audio β’ Updated β’ 2
ASLP-lab/VoiceSculptor-VD
Text-to-Speech β’ 4B β’ Updated β’ 25 β’ 18
ASLP-lab/WenetSpeech-Wu-Speech-Understanding
Updated
ASLP-lab/WenetSpeech-Wu-Speech-Generation
Text-to-Speech β’ Updated β’ 2
datasets 19
ASLP-lab/SongFormBench
Viewer β’ Updated β’ 3.82k β’ 554 β’ 2
ASLP-lab/FMSU-Bench
Updated β’ 14
ASLP-lab/HumDial-FDBench
Updated β’ 198 β’ 2
ASLP-lab/FastTurn-Testset
Updated β’ 55
ASLP-lab/WSC-Train
Preview β’ Updated β’ 464 β’ 120
ASLP-lab/LyricEditBench
Viewer β’ Updated β’ 7.2k β’ 286 β’ 2
ASLP-lab/WenetSpeech-Wu-Bench
Viewer β’ Updated β’ 242 β’ 390 β’ 4
ASLP-lab/WenetSpeech-Wu
Updated β’ 31 β’ 1
ASLP-lab/WenetSpeech-Yue
Updated β’ 433 β’ 41
ASLP-lab/WSC-Eval
Viewer β’ Updated β’ 1.19k β’ 10.9k β’ 7