Hye-jin Shim
Carnegie Mellon University(US)
Publications by Year
Research Areas
Speech Recognition and Synthesis, Speech and Audio Processing, Music and Audio Processing, Digital Media Forensic Detection, Topic Modeling
Most-Cited Works
- → AASIST: Audio Anti-Spoofing Using Integrated Spectro-Temporal Graph Attention Networks(2022)278 cited
- → RawNet: Advanced End-to-End Deep Neural Network Using Raw Waveforms for Text-Independent Speaker Verification(2019)158 cited
- → Improved RawNet with Feature Map Scaling for Text-Independent Speaker Verification Using Raw Waveforms(2020)93 cited
- → A Complete End-to-End Speaker Verification System Using Deep Neural Networks: From Raw Signals to Verification Result(2018)70 cited
- → Avoiding Speaker Overfitting in End-to-End DNNs Using Raw Waveform for Text-Independent Speaker Verification(2018)57 cited
- → Replay Attack Detection with Complementary High-Resolution Information Using End-to-End DNN for the ASVspoof 2019 Challenge(2019)49 cited
- → Short Utterance Compensation in Speaker Verification via Cosine-Based Teacher-Student Learning of Speaker Embeddings(2019)40 cited
- → Knowledge Distillation in Acoustic Scene Classification(2020)32 cited
- → End-to-End Losses Based on Speaker Basis Vectors and All-Speaker Hard Negative Mining for Speaker Verification(2019)24 cited
- → DCASENET: An Integrated Pretrained Deep Neural Network for Detecting and Classifying Acoustic Scenes and Events(2021)22 cited