Heinrich Dinkel
Scholar

Heinrich Dinkel

Google Scholar ID: sn3DsXoAAAAJ
Xiaomi
Computer ScienceAudio processingAudio taggingSound Event DetectionSpoofing detection
Google Scholar↗
Citations & Impact
All-time
Citations
1,509
 
H-index
22
 
i10-index
27
 
Publications
20
 
Co-authors
22
list available
Contact
No contact links provided.
Publications
10 items
ACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding
2026
Cited
0
The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models
2026
Cited
0
DashengTokenizer: One layer is enough for unified audio understanding and generation
2026
Cited
0
MiDashengLM: Efficient Audio Understanding with General Audio Captions
2025
Cited
0
MECAT: A Multi-Experts Constructed Benchmark for Fine-Grained Audio Understanding Tasks
2025
Cited
0
Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders
2025
Cited
0
GLAP: General contrastive audio-text pretraining across domains and languages
2025
Cited
0
X-ARES: A Comprehensive Framework for Assessing Audio Encoder Performance
2025
Cited
0
Resume (English only)
Co-authors
22 total
Kai Yu（俞凯）
Kai Yu（俞凯）
Shanghai Jiao Tong University
Mengyue Wu
Mengyue Wu
Shanghai Jiao Tong University
Yongqing Wang
Yongqing Wang
小米
Junbo Zhang
Junbo Zhang
Xiaomi Inc.
Yanmin Qian
Yanmin Qian
Professor, Shanghai Jiao Tong University
Xuenan Xu
Xuenan Xu
Shanghai Jiao Tong University
Co-author 7
Co-author 7
Shuai Wang
Shuai Wang
Nanjing University