Qingying Zhu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Qingying Zhu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Minchuan Chen
Ping An Technology, Shenzhen, China
3 shared publications - Shaojun Wang
Ping An Technology, Shanghai, China
3 shared publications - Jing Xiao
Ping An Technology, Shenzhen, China
2 shared publications - Jun Yu
University of Science and Technology of China, Hefei, China
2 shared publications - Chenfeng Miao
Ping An Technology, Shanghai, China
1 shared publication - Jing Xiao
Pingan Group Co., Ltd., Shenzhen, China
1 shared publication
Latest Publications
- Open Access
- 23 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 1650-1661
EfficientTTS 2: Variational End-to-End Text-to-Speech Synthesis and Voice Conversion
Recently, the field of Text-to-Speech (TTS) has been dominated by one-stage text-to-waveform models which have significantly improved speech quality compared to two-stage models. In this work, we propose EfficientTTS 2 (EFTS2), a one-stage high-quality end-to-end TTS framework that is fully differentiable and highly efficient. Our method adopts an adversarial training process, with a differentiable aligner and a hierarchical-VAE-based waveform generator. These design choices free the model from the use of external aligners, invertible structures, and complex training procedures as most previous TTS works have. Moreover, we extend EFTS2 to the voice conversion (VC) task and propose EFTS2-VC, an end-to-end VC model that allows high-quality speech-to-speech conversion. Experimental results suggest that the two proposed models achieve better or at least comparable speech quality compared to baseline models, while also providing faster inference speeds and smaller model sizes.
- 23 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Audio, Speech, and Language Processing
- Vol. 32 (23299290) , 1650-1661
Open AccessEfficientTTS 2: Variational End-to-End Text-to-Speech Synthesis and Voice Conversion
Recently, the field of Text-to-Speech (TTS) has been dominated by one-stage text-to-waveform models which have significantly improved speech quality compared to two-stage models. In this work, we propose EfficientTTS 2 (EFTS2), a one-stage high-quality end-to-end TTS framework that is fully differentiable and highly efficient. Our method adopts an adversarial training process, with a differentiable aligner and a hierarchical-VAE-based waveform generator. These design choices free the model from the use of external aligners, invertible structures, and complex training procedures as most previous TTS works have. Moreover, we extend EFTS2 to the voice conversion (VC) task and propose EFTS2-VC, an end-to-end VC model that allows high-quality speech-to-speech conversion. Experimental results suggest that the two proposed models achieve better or at least comparable speech quality compared to baseline models, while also providing faster inference speeds and smaller model sizes.
- Open Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 137-142
Image- and Instance-Level Data Augmentation for Occluded Instance Segmentation
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 137-142
Open AccessImage- and Instance-Level Data Augmentation for Occluded Instance Segmentation
- Open Access
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 151-159
Relative Boundary Modeling: A High-Resolution Cricket Bowl Release Detection Framework with I3D Features
Cricket Bowl Release Detection aims to segment specific portions of bowl release actions occurring in multiple videos, with a focus on detecting the entire time window of this action. Unlike traditional detection tasks that identify action categories at a specific moment, this task involves identifying events that typically span around 100 frames and require recognizing all instances of the bowl release action in the video. Strictly speaking, this task falls under a branch of temporal action detection. With the advancement of deep neural networks, recent works have proposed deep learning-based approaches to address this task. However, due to the challenge of unclear action boundaries in videos, many existing methods perform poorly on the DeepSportradar Cricket Bowl Release Dataset. To more accurately identify specific portions of the bowl release action in videos, we adopt a one-stage architecture based on Relative Boundary Modeling. Specifically, our method consists of three stages. In the first stage, we use the Inflated 3D ConvNet (I3D) model to extract spatio-temporal features from the input videos. In the second stage, we utilize Temporal Action Detection with Relative Boundary Modeling (TriDet) to model the boundaries of the bowl release action's specific portions based on the relative relationships between different time moments, thereby predicting the action's time window. Lastly, as the target events typically span around 100 frames and the predicted time windows may exhibit overlapping regions based on confidence scores, we implement a post-processing step to merge and filter these outputs, resulting in the final submission results. We conducted extensive experiments to demonstrate that our proposed method achieves superior performance. Additionally, we evaluated the training techniques of existing approaches. Our proposed method achieves a PQ score of 0.519, an SQ score of 0.822, and an RQ score of 0.632 on the challenge set of the DeepSportradar Cricket Bowl Release Dataset. Through this approach, our team, USTC\_IAT\_United, won the third place in the first phase of the DeepSportradar Cricket Bowl Release Challenge.
- 29 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 151-159
Open AccessRelative Boundary Modeling: A High-Resolution Cricket Bowl Release Detection Framework with I3D Features
Cricket Bowl Release Detection aims to segment specific portions of bowl release actions occurring in multiple videos, with a focus on detecting the entire time window of this action. Unlike traditional detection tasks that identify action categories at a specific moment, this task involves identifying events that typically span around 100 frames and require recognizing all instances of the bowl release action in the video. Strictly speaking, this task falls under a branch of temporal action detection. With the advancement of deep neural networks, recent works have proposed deep learning-based approaches to address this task. However, due to the challenge of unclear action boundaries in videos, many existing methods perform poorly on the DeepSportradar Cricket Bowl Release Dataset. To more accurately identify specific portions of the bowl release action in videos, we adopt a one-stage architecture based on Relative Boundary Modeling. Specifically, our method consists of three stages. In the first stage, we use the Inflated 3D ConvNet (I3D) model to extract spatio-temporal features from the input videos. In the second stage, we utilize Temporal Action Detection with Relative Boundary Modeling (TriDet) to model the boundaries of the bowl release action's specific portions based on the relative relationships between different time moments, thereby predicting the action's time window. Lastly, as the target events typically span around 100 frames and the predicted time windows may exhibit overlapping regions based on confidence scores, we implement a post-processing step to merge and filter these outputs, resulting in the final submission results. We conducted extensive experiments to demonstrate that our proposed method achieves superior performance. Additionally, we evaluated the training techniques of existing approaches. Our proposed method achieves a PQ score of 0.519, an SQ score of 0.822, and an RQ score of 0.632 on the challenge set of the DeepSportradar Cricket Bowl Release Dataset. Through this approach, our team, USTC\_IAT\_United, won the third place in the first phase of the DeepSportradar Cricket Bowl Release Challenge.