Unsupervised Multi-scale Expressive Speaking Style Modeling with Hierarchical Context Information for Audiobook Speech Synthesis

no code implementations • COLING 2022 • Xueyuan Chen, Shun Lei, Zhiyong Wu, Dong Xu, Weifeng Zhao, Helen Meng

On top of these, a bi-reference attention mechanism is used to align both local-scale reference style embedding sequence and local-scale context style embedding sequence with corresponding phoneme embedding sequence.

Speech Synthesis Text to Speech

MBTFNet: Multi-Band Temporal-Frequency Neural Network For Singing Voice Enhancement

no code implementations • 6 Oct 2023 • Weiming Xu, Zhouxuan Chen, Zhili Tan, Shubo Lv, Runduo Han, Wenjiang Zhou, Weifeng Zhao, Lei Xie

A typical neural speech enhancement (SE) approach mainly handles speech and noise mixtures, which is not optimal for singing voice enhancement scenarios.

Music Source Separation Speech Enhancement

WideResNet with Joint Representation Learning and Data Augmentation for Cover Song Identification

no code implementations • Interspeech 2022 • Shichao Hu, Bin Zhang, JinHong Lu, Yiliang Jiang, Wucheng Wang, Lingcheng Kong, Weifeng Zhao, Tao Jiang

In this paper, we propose a novel framework for CSI based on a joint representation learning method inspired by multi-task learning.

Cover song identification Data Augmentation +8