421 citations
- University of Chinese Academy of SciencesCN28 papers
- Chinese Academy of SciencesCN20 papers
- Institute of AutomationCN16 papers
- Beijing Academy of Artificial IntelligenceCN8 papers
- Shandong Institute of AutomationCN7 papers
- Institute of Computing TechnologyCN5 papers
- University of Science and Technology of ChinaCN3 papers
- Tongji UniversityCN2 papers
- Aerospace Information Research InstituteCN1 paper
- Alibaba Group (United States)US1 paper
- Anhui UniversityCN1 paper
- Association for Computing MachineryUS1 paper
Showing eess.ASShow all
3 papers · 1 filter
eess.AS2021
FSR: Accelerating the Inference Process of Transducer-Based Models by Applying Fast-Skip Regularization
Zhengkun Tian, Jiangyan Yi, Ye Bai +3
Transducer-based models, such as RNN-Transducer and transformer-transducer, have achieved great success in speech recognition. A typical transducer model decodes the output sequenc…
eess.AS2019★ 17 cited
Unsupervised Representation Learning with Future Observation Prediction for Speech Emotion Recognition
Zheng Lian, Jianhua Tao, Bin Liu +1
Prior works on speech emotion recognition utilize various unsupervised learning approaches to deal with low-resource samples. However, these methods pay less attention to modeling…
eess.AS2019★ 85 cited
Self-Attention Transducers for End-to-End Speech Recognition
Zhengkun Tian, Jiangyan Yi, Jianhua Tao +2
Recurrent neural network transducers (RNN-T) have been successfully applied in end-to-end speech recognition. However, the recurrent structure makes it difficult for parallelizatio…