26 citations · 110 across the 20 of their papers we have counts for
20 papers
Fully Hyperbolic Rotation for Knowledge Graph Embedding
Qiuyu Liang, Weihua Wang, Feilong Bao +1
Hyperbolic rotation is commonly used to effectively model knowledge graphs and their inherent hierarchies. However, existing hyperbolic rotation models rely on logarithmic and expo…
L^2GC:Lorentzian Linear Graph Convolutional Networks for Node Classification
Qiuyu Liang, Weihua Wang, Feilong Bao +1
Linear Graph Convolutional Networks (GCNs) are used to classify the node in the graph data. However, we note that most existing linear GCN models perform neural network operations…
Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion
Rui Liu, Jinhua Zhang, Guanglai Gao +1
Audio Deepfake Detection (ADD) aims to detect the fake audio generated by text-to-speech (TTS), voice conversion (VC) and replay, etc., which is an emerging topic. Traditionally we…
MnTTS2: An Open-Source Multi-Speaker Mongolian Text-to-Speech Synthesis Dataset
Kailin Liang, Bin Liu, Yifan Hu +3
Text-to-Speech (TTS) synthesis for low-resource languages is an attractive research issue in academia and industry nowadays. Mongolian is the official language of the Inner Mongoli…
Explicit Intensity Control for Accented Text-to-speech
Rui Liu, Haolin Zuo, De Hu +2
Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a variant of the standard version (L1). How to control the intensity of accent in the proces…
FCTalker: Fine and Coarse Grained Context Modeling for Expressive Conversational Speech Synthesis
Yifan Hu, Rui Liu, Guanglai Gao +1
Conversational Text-to-Speech (TTS) aims to synthesis an utterance with the right linguistic and affective prosody in a conversational context. The correlation between the current…
Exploiting modality-invariant feature for robust multimodal emotion recognition with missing modalities
Haolin Zuo, Rui Liu, Jinming Zhao +2
Multimodal emotion recognition leverages complementary information across modalities to gain performance. However, we cannot guarantee that the data of all modalities are always pr…
A Deep Investigation of RNN and Self-attention for the Cyrillic-Traditional Mongolian Bidirectional Conversion
Muhan Na, Rui Liu, Feilong +1
Cyrillic and Traditional Mongolian are the two main members of the Mongolian writing system. The Cyrillic-Traditional Mongolian Bidirectional Conversion (CTMBC) task includes two c…
MnTTS: An Open-Source Mongolian Text-to-Speech Synthesis Dataset and Accompanied Baseline
Yifan Hu, Pengkai Yin, Rui Liu +2
This paper introduces a high-quality open-source text-to-speech (TTS) synthesis dataset for Mongolian, a low-resource language spoken by over 10 million people worldwide. The datas…
Controllable Accented Text-to-Speech Synthesis
Rui Liu, Berrak Sisman, Guanglai Gao +1
Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a variant of the standard version (L1). Accented TTS synthesis is challenging as L2 is diffe…
Accurate Emotion Strength Assessment for Seen and Unseen Speech Based on Data-Driven Deep Learning
Rui Liu, Berrak Sisman, Björn Schuller +2
Emotion classification of speech and assessment of the emotion strength are required in applications such as emotional text-to-speech and voice conversion. The emotion attribute ra…
Guided Training: A Simple Method for Single-channel Speaker Separation
Hao Li, Xueliang Zhang, Guanglai Gao
Deep learning has shown a great potential for speech separation, especially for speech and non-speech separation. However, it encounters permutation problem for multi-speaker separ…
Modeling Prosodic Phrasing with Multi-Task Learning in Tacotron-based TTS
Rui Liu, Berrak Sisman, Feilong Bao +2
Tacotron-based end-to-end speech synthesis has shown remarkable voice quality. However, the rendering of prosody in the synthesized speech remains to be improved, especially for lo…
Expressive TTS Training with Frame and Style Reconstruction Loss
Rui Liu, Berrak Sisman, Guanglai Gao +1
We propose a novel training strategy for Tacotron-based text-to-speech (TTS) system to improve the expressiveness of speech. One of the key challenges in prosody modeling is the la…
An Edge Information and Mask Shrinking Based Image Inpainting Approach
Huali Xu, Xiangdong Su, Meng Wang +2
In the image inpainting task, the ability to repair both high-frequency and low-frequency information in the missing regions has a substantial influence on the quality of the resto…
SNR-Based Teachers-Student Technique for Speech Enhancement
Xiang Hao, Xiangdong Su, Zhiyu Wang +3
It is very challenging for speech enhancement methods to achieves robust performance under both high signal-to-noise ratio (SNR) and low SNR simultaneously. In this paper, we propo…
Sub-Band Knowledge Distillation Framework for Speech Enhancement
Xiang Hao, Shixue Wen, Xiangdong Su +3
In single-channel speech enhancement, methods based on full-band spectral features have been widely studied. However, only a few methods pay attention to non-full-band spectral fea…
WaveTTS: Tacotron-based TTS with Joint Time-Frequency Domain Loss
Rui Liu, Berrak Sisman, Feilong Bao +2
Tacotron-based text-to-speech (TTS) systems directly synthesize speech from text input. Such frameworks typically consist of a feature prediction network that maps character sequen…
Teacher-Student Training for Robust Tacotron-based TTS
Rui Liu, Berrak Sisman, Jingdong Li +3
While neural end-to-end text-to-speech (TTS) is superior to conventional statistical methods in many ways, the exposure bias problem in the autoregressive models remains an issue t…
Integrated Speech Enhancement Method Based on Weighted Prediction Error and DNN for Dereverberation and Denoising
Hao Li, Xueliang Zhang, Hui Zhang +1
Both reverberation and additive noises degrade the speech quality and intelligibility. Weighted prediction error (WPE) method performs well on the dereverberation but with limitati…