Boyang Lyu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Boyang Lyu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chunxiao Fan
Beijing University of Posts and Telecommunications
1 shared publication Jiangwan Zhou
Beijing University of Posts and Telecommunications , Beijing 100876, China
1 shared publication- Jiangwan Zhou
Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Kai Hong
Key Laboratory of Work Safety Intelligent Monitoring, School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China
1 shared publication - Nannan Hu
School of Communication and Electronic Engineering, Shandong Normal University, Jinan 250358, China
1 shared publication - Panzi Zhao
Beijing University of Posts and Telecommunications , Beijing 100876, China
1 shared publication
Latest Publications
- 7 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
NAR-SREC: Nonautoregressive End-to-End Speech Recognition With Error Correction Decoder
With the popularity of mobile smart devices, speech recognition utilizes the speech signals received by sensors to quickly find the most likely text or command through non-autoregressive (NAR) inference, providing a solid foundation for human-computer interaction. However, NAR inference ignores the dependencies between words, which significantly degrades recognition accuracy. To alleviate this problem, we propose a novel Non-Autoregressive End-to-End Speech Recognition with Error Correction Decoder (NAR-SREC), which improves recognition accuracy and inference speed by closely collaborating three core components. Specifically, we first design a new Context-Association CTC (CACTC) to incorporate explicit linguistic information into the output condition term for NAR inference, which enhances inter-word relationship learning. Then, we propose a new BERT-augmented Module to simultaneously model the target sequence and source sequence, where the former provides linguistic information to the CACTC, and the latter performs error probability detection. Finally, we integrate a NAR Error Correction (NAR-EC) decoder for fast error correction, which focuses on correcting incorrect tokens to further reduce the insertion or substitution errors caused by the insufficient inter-word relationship. Extensive experiments on Aishell-1 and Librispeech show that NAR-SREC significantly improves the recognition accuracy compared with other advanced NAR methods, achieving a better trade-off between speed and performance.
- 7 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-14
NAR-SREC: Nonautoregressive End-to-End Speech Recognition With Error Correction Decoder
With the popularity of mobile smart devices, speech recognition utilizes the speech signals received by sensors to quickly find the most likely text or command through non-autoregressive (NAR) inference, providing a solid foundation for human-computer interaction. However, NAR inference ignores the dependencies between words, which significantly degrades recognition accuracy. To alleviate this problem, we propose a novel Non-Autoregressive End-to-End Speech Recognition with Error Correction Decoder (NAR-SREC), which improves recognition accuracy and inference speed by closely collaborating three core components. Specifically, we first design a new Context-Association CTC (CACTC) to incorporate explicit linguistic information into the output condition term for NAR inference, which enhances inter-word relationship learning. Then, we propose a new BERT-augmented Module to simultaneously model the target sequence and source sequence, where the former provides linguistic information to the CACTC, and the latter performs error probability detection. Finally, we integrate a NAR Error Correction (NAR-EC) decoder for fast error correction, which focuses on correcting incorrect tokens to further reduce the insertion or substitution errors caused by the insufficient inter-word relationship. Extensive experiments on Aishell-1 and Librispeech show that NAR-SREC significantly improves the recognition accuracy compared with other advanced NAR methods, achieving a better trade-off between speed and performance.
- Open Access
- 1 August 2023
- Published by AIP Publishing in AIP Advances
- Vol. 13 (8)
DSNet: Dual-stream multi-scale fusion network for low-quality 3D face recognition
3D face recognition (FR) has become increasingly widespread due to the illumination invariance and pose robustness of 3D face data. Most existing 3D FR methods can only achieve excellent performance on complete and smooth faces. However, low-quality 3D FR with missing facial features still suffers from insufficient discriminative feature extraction for visible face regions. In this paper, we propose a dual-stream multi-scale fusion network (DSNet) for low-quality 3D FR. First, in the first stream, we design a new multi-scale local and global feature fusion network, which consists of an enhanced shallow feature extraction module, an enhanced deep feature extraction module, and a layered multi-scale feature correlation fusion module, aiming to obtain more discriminative details and category information of the facial visible region, reducing the interference of similar features and the redundancy of the same features. Second, we also introduced a capsule network as the second stream to enhance the expression of 3D facial spatial position information, thereby further improving the performance of low-quality 3D FR with missing facial features. We conduct extensive experiments on low-quality datasets (Lock3DFace, KinectFaceDB, and IIIT-D) and cross-quality datasets synthesized by Bosphorus. These results show that our proposed DSNet can achieve state-of-the-art recognition performance and exhibit excellent performance on low-quality 3D faces with missing facial features.
- 1 August 2023
- Published by AIP Publishing in AIP Advances
- Vol. 13 (8)
Open AccessDSNet: Dual-stream multi-scale fusion network for low-quality 3D face recognition
3D face recognition (FR) has become increasingly widespread due to the illumination invariance and pose robustness of 3D face data. Most existing 3D FR methods can only achieve excellent performance on complete and smooth faces. However, low-quality 3D FR with missing facial features still suffers from insufficient discriminative feature extraction for visible face regions. In this paper, we propose a dual-stream multi-scale fusion network (DSNet) for low-quality 3D FR. First, in the first stream, we design a new multi-scale local and global feature fusion network, which consists of an enhanced shallow feature extraction module, an enhanced deep feature extraction module, and a layered multi-scale feature correlation fusion module, aiming to obtain more discriminative details and category information of the facial visible region, reducing the interference of similar features and the redundancy of the same features. Second, we also introduced a capsule network as the second stream to enhance the expression of 3D facial spatial position information, thereby further improving the performance of low-quality 3D FR with missing facial features. We conduct extensive experiments on low-quality datasets (Lock3DFace, KinectFaceDB, and IIIT-D) and cross-quality datasets synthesized by Bosphorus. These results show that our proposed DSNet can achieve state-of-the-art recognition performance and exhibit excellent performance on low-quality 3D faces with missing facial features.