20 citations · 24 across the 5 of their papers we have counts for
5 papers
Enhanced Memory Network: The novel network structure for Symbolic Music Generation
Jin Li, Haibin Liu, Nan Yan +1
Symbolic melodies generation is one of the essential tasks for automatic music generation. Recently, models based on neural networks have had a significant influence on generating…
Unsupervised Cross-Lingual Speech Emotion Recognition Using Pseudo Multilabel
Jin Li, Nan Yan, Lan Wang
Speech Emotion Recognition (SER) in a single language has achieved remarkable results through deep learning approaches in the last decade. However, cross-lingual SER remains a chal…
A Multi-level Acoustic Feature Extraction Framework for Transformer Based End-to-End Speech Recognition
Jin Li, Rongfeng Su, Xurong Xie +2
Transformer based end-to-end modelling approaches with multiple stream inputs have been achieved great success in various automatic speech recognition (ASR) tasks. An important iss…
FDN: Finite Difference Network with Hierarchical Convolutional Features for Text-independent Speaker Verification
Jin Li, Nan Yan, Lan Wang
In recent years, using raw waveforms as input for deep networks has been widely explored for the speaker verification system. For example, RawNet and RawNet2 extracted speaker's fe…
Bayesian Learning for Deep Neural Network Adaptation
Xurong Xie, Xunying Liu, Tan Lee +1
A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences. Speaker adaptation techn…