Meta-learning for short utterance speaker recognition with imbalance length pairs
In practical settings, a speaker recognition system needs to identify a speaker given a short
utterance, while the enrollment utterance may be relatively long. However, existing speaker …
utterance, while the enrollment utterance may be relatively long. However, existing speaker …
SYENet: A simple yet effective network for multiple low-level vision tasks with real-time performance on mobile device
W Gou, Z Yi, Y Xiang, S Li, Z Liu… - Proceedings of the …, 2023 - openaccess.thecvf.com
With the rapid development of AI hardware accelerators, applying deep learning-based
algorithms to solve various low-level vision tasks on mobile devices has gradually become …
algorithms to solve various low-level vision tasks on mobile devices has gradually become …
[HTML][HTML] Deep learning-based technique for remote sensing image enhancement using multiscale feature fusion
M Zhao, R Yang, M Hu, B Liu - Sensors, 2024 - mdpi.com
The present study proposes a novel deep-learning model for remote sensing image
enhancement. It maintains image details while enhancing brightness in the feature …
enhancement. It maintains image details while enhancing brightness in the feature …
Supervised attention for speaker recognition
The recently proposed self-attentive pooling (SAP) has shown good performance in several
speaker recognition systems. In SAP systems, the context vector is trained end-to-end …
speaker recognition systems. In SAP systems, the context vector is trained end-to-end …
Attention-based broad self-guided network for low-light image enhancement
Z Chen, Y Liang, M Du - 2022 26th International Conference on …, 2022 - ieeexplore.ieee.org
Low-light image enhancement is widely used in many fields, such as target detection, face
recognition, and image segmentation. In recent years, Deep Learning methods have …
recognition, and image segmentation. In recent years, Deep Learning methods have …
[PDF][PDF] Light-Weight Speaker Verification with Global Context Information.
In this paper, we propose a light-weight speaker verification (SV) system that utilizes the
characteristics of utterancelevel global features. Many recent SV tasks employ convolutional …
characteristics of utterancelevel global features. Many recent SV tasks employ convolutional …
Recursive Attentive Pooling for Extracting Speaker Embeddings from Multi-Speaker Recordings
This paper proposes a method for extracting speaker embedding for each speaker from a
variable-length recording containing multiple speakers. Speaker embeddings are crucial not …
variable-length recording containing multiple speakers. Speaker embeddings are crucial not …
A Region Based Non-overlapping Reference Speech Estimation Method for Speaker Extraction
Y Zhang, Z Li, B Liu, H Fan, Y Yang, Q Yang - International Conference on …, 2024 - Springer
Speaker extraction is a technique that separates the target speech from multi-talker mixtures
using a priori information about the target speaker, such as pre-enrolled reference speech …
using a priori information about the target speaker, such as pre-enrolled reference speech …