8 citations · 15 across the 12 of their papers we have counts for
12 papers
PromptEVC: Controllable Emotional Voice Conversion with Natural Language Prompts
Tianhua Qi, Shiyan Wang, Cheng Lu +4
Controllable emotional voice conversion (EVC) aims to manipulate emotional expressions to increase the diversity of synthesized speech. Existing methods typically rely on predefine…
Towards Realistic Emotional Voice Conversion using Controllable Emotional Intensity
Tianhua Qi, Shiyan Wang, Cheng Lu +3
Realistic emotional voice conversion (EVC) aims to enhance emotional diversity of converted audios, making the synthesized voices more authentic and natural. To this end, we propos…
Temporal Label Hierachical Network for Compound Emotion Recognition
Sunan Li, Hailun Lian, Cheng Lu +5
The emotion recognition has attracted more attention in recent decades. Although significant progress has been made in the recognition technology of the seven basic emotions, exist…
PAVITS: Exploring Prosody-aware VITS for End-to-End Emotional Voice Conversion
Tianhua Qi, Wenming Zheng, Cheng Lu +2
In this paper, we propose Prosody-aware VITS (PAVITS) for emotional voice conversion (EVC), aiming to achieve two major objectives of EVC: high content naturalness and high emotion…
Emotion-Aware Contrastive Adaptation Network for Source-Free Cross-Corpus Speech Emotion Recognition
Yan Zhao, Jincen Wang, Cheng Lu +4
Cross-corpus speech emotion recognition (SER) aims to transfer emotional knowledge from a labeled source corpus to an unlabeled corpus. However, prior methods require access to sou…
Speech Swin-Transformer: Exploring a Hierarchical Transformer with Shifted Windows for Speech Emotion Recognition
Yong Wang, Cheng Lu, Hailun Lian +4
Swin-Transformer has demonstrated remarkable success in computer vision by leveraging its hierarchical feature representation based on Transformer. In speech signals, emotional inf…
Improving Speaker-independent Speech Emotion Recognition Using Dynamic Joint Distribution Adaptation
Cheng Lu, Yuan Zong, Hailun Lian +3
In speaker-independent speech emotion recognition, the training and testing samples are collected from diverse speakers, leading to a multi-domain shift challenge across the featur…
Towards Domain-Specific Cross-Corpus Speech Emotion Recognition Approach
Yan Zhao, Yuan Zong, Hailun Lian +3
Cross-corpus speech emotion recognition (SER) poses a challenge due to feature distribution mismatch, potentially degrading the performance of established SER methods. In this pape…
Learning to Rank Onset-Occurring-Offset Representations for Micro-Expression Recognition
Jie Zhu, Yuan Zong, Jingang Shi +3
This paper focuses on the research of micro-expression recognition (MER) and proposes a flexible and reliable deep learning method called learning to rank onset-occurring-offset re…
Layer-Adapted Implicit Distribution Alignment Networks for Cross-Corpus Speech Emotion Recognition
Yan Zhao, Yuan Zong, Jincen Wang +4
In this paper, we propose a new unsupervised domain adaptation (DA) method called layer-adapted implicit distribution alignment networks (LIDAN) to address the challenge of cross-c…
Learning Local to Global Feature Aggregation for Speech Emotion Recognition
Cheng Lu, Hailun Lian, Wenming Zheng +3
Transformer has emerged in speech emotion recognition (SER) at present. However, its equal patch division not only damages frequency information but also ignores local emotion corr…
Speech Emotion Recognition via an Attentive Time-Frequency Neural Network
Cheng Lu, Wenming Zheng, Hailun Lian +4
Spectrogram is commonly used as the input feature of deep neural networks to learn the high(er)-level time-frequency pattern of speech signal for speech emotion recognition (SER).…