13 Papers
26 Citations
Yongjun He is an academic researcher from Harbin University of Science and Technology. The author has contributed to research in topics: Computer science & Sparse approximation. The author has an hindex of 4, co-authored 5 publications.
Chat about Author
Papers
Optimization of learned dictionary for sparse coding in speech processing
TL;DR: The inherent assumptions of sparse coding are analyzed and show that distortion can be caused if the assumptions do not hold true, and two methods to optimize a given dictionary by removing unimportant atoms and harmful atoms, respectively are proposed.
14
Spectrum enhancement with sparse coding for robust speech recognition
TL;DR: A novel method first finds out the atoms which represent the noise sparsely, and then selectively ignores them in the reconstruction of speech to reduce the residual noise, and speech features are then extracted from the enhanced spectrum for speech recognition.
14
Graph-Based Spectro-Temporal Dependency Modeling for Anti-Spoofing
Feng Chen,Shiwen Deng,Tieran Zheng,Yongjun He,Jiqing Han +4 more
- 04 Jun 2023
TL;DR: In this article , a graph neural network is employed to model the dependency and incorporate prior knowledge into the graph by designing the graph structure and edge weight, which forces the network to pay more attention to potential relationships.
13
A bilevel framework for joint optimization of session compensation and classification for speaker identification
TL;DR: This paper proposes a bilevel framework to jointly optimize session compensation and classifier to enhance the relationship between the two stages and can be more robust to complex session variability.
9
A new framework for robust speech recognition in complex channel environments
TL;DR: Experimental results show that the proposed framework can substantially improve the performance of ASR systems in complex channel environments.
8