639 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Tsinghua UniversityCN97 papers
- Shenzhen UniversityCN27 papers
- Tsinghua–Berkeley Shenzhen InstituteCN25 papers
- Harbin Institute of TechnologyCN13 papers
- Peng Cheng LaboratoryCN10 papers
- Tencent (China)CN9 papers
- Chinese University of Hong KongHK6 papers
- Chinese Academy of SciencesCN5 papers
- Huawei Technologies (China)CN5 papers
- Southern University of Science and TechnologyCN5 papers
- University of Science and Technology of ChinaCN5 papers
- Beijing University of Posts and TelecommunicationsCN4 papers
8 papers · 1 filter
Audio-to-Score Transcription using Pre-trained Features, Data Augmentation, and the New SheetSage-A2S Dataset
Eoin Cummins, Zhongyi Huang, Alexandre D'Hooge +2
Existing audio-to-score (A2S) systems primarily focus on classical music, and the application to popular music remains underexplored. This paper first presents the new SheetSage-A2…
Frame-level Temporal Difference Learning for Partial Deepfake Speech Detection
Menglu Li, Xiao-Ping Zhang, Lian Zhao
Detecting partial deepfake speech is essential due to its potential for subtle misinformation. However, existing methods depend on costly frame-level annotations during training, l…
VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling
Yixuan Zhou, Xiaoyu Qin, Zeyu Jin +5
Recent AIGC systems possess the capability to generate digital multimedia content based on human language instructions, such as text, image and video. However, when it comes to spe…
A Survey on Speech Deepfake Detection
Menglu Li, Yasaman Ahmadiadli, Xiao-Ping Zhang
The availability of smart devices leads to an exponential increase in multimedia content. However, advancements in deep learning have also enabled the creation of highly sophistica…
Exploring Multi-Modal Control in Music-Driven Dance Generation
Ronghui Li, Yuqin Dai, Yachao Zhang +4
Existing music-driven 3D dance generation methods mainly concentrate on high-quality dance generation, but lack sufficient control during the generation process. To address these i…
Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representation
Jiaxu Zhu, Weinan Tong, Yaoxun Xu +6
Mapping two modalities, speech and text, into a shared representation space, is a research topic of using text-only data to improve end-to-end automatic speech recognition (ASR) pe…
Improving Mandarin Prosodic Structure Prediction with Multi-level Contextual Information
Jie Chen, Changhe Song, Deyi Tuo +4
For text-to-speech (TTS) synthesis, prosodic structure prediction (PSP) plays an important role in producing natural and intelligible speech. Although inter-utterance linguistic in…
LightGrad: Lightweight Diffusion Probabilistic Model for Text-to-Speech
Jie Chen, Xingchen Song, Zhendong Peng +3
Recent advances in neural text-to-speech (TTS) models bring thousands of TTS applications into daily life, where models are deployed in cloud to provide services for customs. Among…