arxiv:2509.13395
Haolong Zheng
MagicLuke
AI & ML interests
Speech
Recent Activity
authored
a paper
about 1 month ago
TICL: Text-Embedding KNN For Speech In-Context Learning Unlocks Speech
Recognition Abilities of Large Multimodal Models
updated
a dataset
3 months ago
SST-UIUC/common_voice_en
published
a dataset
3 months ago
SST-UIUC/common_voice_en
Organizations
models
8
MagicLuke/ecapa-tdnn-speaker-encoder
Feature Extraction
•
16.2M
•
Updated
•
1
MagicLuke/TrainingFreeTTS-SpeakerEncoder
Updated
MagicLuke/TrainingFreeTTS-PhonemeClassifier
0.6B
•
Updated
MagicLuke/TF-TTS-PhonemeClassifier
Updated
MagicLuke/Wav2Vec2-Base-LS360-Myst109
Automatic Speech Recognition
•
94.4M
•
Updated
MagicLuke/Wav2Vec2-Base-myst-myst109
Automatic Speech Recognition
•
94.4M
•
Updated
MagicLuke/Wav2Vec2Conformer-MyST-MyST109
0.2B
•
Updated
MagicLuke/Wav2Vec2-MyST
95M
•
Updated
datasets
19
MagicLuke/RedmondSentenceRecall
Viewer
•
Updated
•
423k
•
3
MagicLuke/en
Updated
•
3
MagicLuke/eng-zh-cs-sme
Viewer
•
Updated
•
123k
•
18
MagicLuke/ASCEND-phoneme
Viewer
•
Updated
•
38.8k
•
18
MagicLuke/common_voice_17_0
Viewer
•
Updated
•
28.7k
•
21
MagicLuke/cmu-arctic
Viewer
•
Updated
•
46.7k
•
6
MagicLuke/GLOBE_V2
Viewer
•
Updated
•
542k
•
11
MagicLuke/hisp-eng
Viewer
•
Updated
•
400
•
5
MagicLuke/l2-arctic
Viewer
•
Updated
•
107k
•
1
MagicLuke/MyST
Viewer
•
Updated
•
714k
•
15
•
1