Author Info
Name
Affiliation
Papers
YAN SONG
Univ Sci & Tech China, Dept EEIS, Huang Shan Rd 4, Hefei 230027, Anhui, Peoples R China
87
Collaborators
Citations 
PageRank 
145
734
51.98
Referers 
Referees 
References 
1607
1580
799
Search Limit
1001000
Title
Citations
PageRank
Year
Frontend Attributes Disentanglement for Speech Emotion Recognition.00.342022
Class-Aware Distribution Alignment based Unsupervised Domain Adaptation for Speaker Verification00.342022
Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition50.412022
Self-Supervised Representation Learning for Unsupervised Anomalous Sound Detection Under Domain Shift00.342022
Skip-attention encoder–decoder framework for human motion prediction10.352022
Domain Robust Deep Embedding Learning for Speaker Recognition00.342022
Cross-Lingual Self-training to Learn Multilingual Representation for Low-Resource Speech Recognition00.342022
Spatiotemporal Perturbation Based Dynamic Consistency for Semi-supervised Temporal Action Detection00.342022
X-Invariant Contrastive Augmentation and Representation Learning for Semi-Supervised Skeleton-Based Action Recognition00.342022
Progressive enhancement network with pseudo labels for weakly supervised temporal action localization00.342022
Acoustic Feature Shuffling Network for Text-independent Speaker Verification00.342022
An Improved Mean Teacher Based Method for Large Scale Weakly Labeled Semi-Supervised Sound Event Detection10.362021
Towards Integration of Domain Knowledge-Guided Feature Engineering and Deep Feature Learning in Surface Electromyography-Based Hand Movement Recognition00.342021
Variance Normalised Features For Language And Dialect Discrimination00.342021
AN EFFECTIVE DEEP EMBEDDING LEARNING METHOD BASED ON DENSE-RESIDUAL NETWORKS FOR SPEAKER VERIFICATION00.342021
Segment boundary detection directed attention for online end-to-end speech recognition.00.342020
Exploring Unknown States with Action Balance00.342020
An Effective Perturbation Based Semi-Supervised Learning Method for Sound Event Detection.00.342020
Task-Aware Mean Teacher Method for Large Scale Weakly Labeled Semi-Supervised Sound Event Detection00.342020
Reinforcement Learning with Action-Specific Focuses in Video Games00.342020
Time-frequency feature fusion for noise-robust audio event classification10.362020
Speaker to Emotion: Domain Adaptation for Speech Emotion Recognition with Residual Adapters00.342019
Temporal Action Localization Based on Temporal Evolution Model and Multiple Instance Learning.00.342019
Knowledge Distillation from Multilingual and Monolingual Teachers for End-to-End Multilingual Speech Recognition00.342019
Triplet-Center Loss Based Deep Embedding Learning Method for Speaker Verification00.342019
Learning Adaptive Downsampling Encoding for Online End-to-End Speech Recognition00.342019
A Conditional Generative Model for Speech Enhancement.00.342018
A Capsule based Approach for Polyphonic Sound Event Detection.00.342018
Effective Action Detection Using Temporal Context and Posterior Probability of Length.00.342018
LID-Senones and Their Statistics for Language Identification.00.342018
Concurrence-Aware Long Short-Term Sub-Memories for Person-Person Action Recognition.90.492017
End-To-End Language Identification Using High-Order Utterance Representation With Bilinear Pooling10.362017
Compact convolutional neural network transfer learning for small-scale image classification.10.352016
Local structure based multi-phase collaborative representation for face recognition with single sample per person.150.502016
Improved i-Vector Representation for Speaker Diarization20.372016
Deep Bottleneck Feature for Image Classification10.362015
Describing Trajectory of Surface Patch for Human Action Recognition on RGB and Depth Videos150.552015
Robust Sound Event Classification Using Deep Neural Networks501.642015
Mouth State Detection From Low-Frequency Ultrasonic Reflection00.342015
Improved Language Identification Using Deep Bottleneck Network20.382015
Deep Bottleneck Network Based I-Vector Representation For Language Identification20.372015
Local structure based sparse representation for face recognition with single sample per person40.412014
Performance evaluation of deep bottleneck features for spoken language identification00.342014
Lane marking detection based on adaptive threshold segmentation and road classification20.382014
A spectral based visual matching method for image classification00.342014
Body Surface Context: A New Robust Feature for Action Recognition From Depth Videos270.702014
Task-aware deep bottleneck features for spoken language identification.20.372014
Real-Time Head Pose Estimation by RGB-D Camera.00.342013
Robust Lane Marking Detection Under Different Road Conditions50.572013
Phoneme variation based synthesized speech discrimination for speaker verification00.342013
  • 1
  • 2
  • 50 / page