95 citations
- Shenzhen Technology UniversityCN9 papers
- Chang Gung Memorial HospitalTW6 papers
- Beijing University of Posts and TelecommunicationsCN5 papers
- National Institutes of Health Clinical CenterUS5 papers
- University of Science and Technology of ChinaCN5 papers
- Beijing Institute of TechnologyCN3 papers
- Johns Hopkins UniversityUS3 papers
- Alibaba Group (China)CN2 papers
- Association for Computing MachineryUS2 papers
- China Medical UniversityTW2 papers
- First Affiliated Hospital Zhejiang UniversityCN2 papers
- Huazhong University of Science and TechnologyCN2 papers
Showing 2021 · eess.ASShow all
3 papers · 2 filters
eess.AS2021
Loss Prediction: End-to-End Active Learning Approach For Speech Recognition
Jian Luo, Jianzong Wang, Ning Cheng +1
End-to-end speech recognition systems usually require huge amounts of labeling resource, while annotating the speech data is complicated and expensive. Active learning is the solut…
eess.AS2021★ 2 cited
Unidirectional Memory-Self-Attention Transducer for Online Speech Recognition
Jian Luo, Jianzong Wang, Ning Cheng +1
Self-attention models have been successfully applied in end-to-end speech recognition systems, which greatly improve the performance of recognition accuracy. However, such attentio…
eess.AS2021★ 4 cited
LVCNet: Efficient Condition-Dependent Modeling Network for Waveform Generation
Zhen Zeng, Jianzong Wang, Ning Cheng +1
In this paper, we propose a novel conditional convolution network, named location-variable convolution, to model the dependencies of the waveform sequence. Different from the use o…