Filter dates
Overview
- acoustic features
- music information retrieval
- activity recognition
- indoor positioning
- wifi
Publications
Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment.
CoRR
Robust Singing Voice Transcription Serves Synthesis.
ACL (1)
CrossHAR: Generalizing Cross-dataset Human Activity Recognition via Hierarchical Self-Supervised Pretraining.
Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.
Where Have You Been? A Study of Privacy Risk for Point-of-Interest Recommendation.
KDD
Self-Supervised Singing Voice Pre-Training towards Speech-to-Singing Conversion.
CoRR
Paths2Pair: Meta-path Based Link Prediction in Billion-Scale Commercial Heterogeneous Graphs.
KDD