Junqing Peng

Publications

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

中文期刊文章

  1. 基于多模态大模型的具身智能体研究进展与展望 (2025), 《大数据》,11 (03),(CCF-T2)
  2. 基于深度卷积和自注意力机制的端到端地震波降噪方法 (2025), 《大数据》(CCF-T2)
  3. 节奏舞者:基于关键动作转换图和有条件姿态插值网络的3D舞蹈生成方法研究 (2023), 《大数据》,9 (01),(CCF-T2)