Junqing Peng
Publications
- Attention-weighted Centered Kernel Alignment for Knowledge Distillation in Large Audio-Language Models Applied to Speech Emotion Recognition (2026), In ICASSP2026 (CCF-B)
- EMO-RL: Emotion-Rule-Based Reinforcement Learning Enhanced Audio-Language Model for Generalized Speech Emotion Recognition (2025), In EMNLP2025 (CCF-B)
- Generalized Audio Deepfake Detection Using Frame-level Latent Information Entropy (2025), In ICME2025 (CCF-B)
- ACCon: Angle-Compensated Contrastive Regularizer for Deep Regression (2025), In AAAI2025 (CCF-A)
- Retrieval-Augmented Audio Deepfake Detection (2024), In ICMR2024 (CCF-B)
- Efficient Multi-Model Fusion with Adversarial Complementary Representation Learning (2024), In IJCNN2024 (CCF-C)
- VoiceExtender: Short-utterance Text-independent Speaker Verification with Guided Diffusion Model (2023), In ASRU2023
- SVVAD: Personal Voice Activity Detection for Speaker Verification (2023), In INTERSPEECH2023 (CCF-C)
- Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General Sound Classification (2023), In ICASSP2023 (CCF-B)
- SVLDL: Improved Speaker Age Estimation Using Selective Variance Label Distribution Learning (2022), In SLT2022
- SpeechEQ: Speech Emotion Recognition based on Multi-scale Unified Datasets and Multitask Learning (2022), In INTERSPEECH2022 (CCF-C)
- Towards Speaker Age Estimation With Label Distribution Learning (2022), In ICASSP2022 (CCF-B)
- A Robust Speaker Clustering Method Based on Discrete Tied Variational Autoencoder (2020), In ICASSP2020 (CCF-B)
- Composer4Everyone: Automatic Music Generation with Audio Motif (2019), In MIPR2019