Junyi Peng

发表

Effective Phase Encoding for End-To-End Speaker Verification

Jan Cernocký, Jianzong Wang, Lukas Burget, 2021, Interspeech.

Parameter-efficient transfer learning of pre-trained Transformer models for speaker verification using adapters

Junyi Peng, Rongzhi Gu, Themos Stafylakis, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform

Jing Xiao, Jianzong Wang, Xiaoyang Qu, 2021, Interspeech.

Learnable Sparse Filterbank for Speaker Verification

L. Burget, Oldrich Plchot, Junyi Peng, 2022, INTERSPEECH.

Progressive Contrastive Learning for Self-Supervised Text-Independent Speaker Verification

Junyi Peng, Dong Yu, Chunlei Zhang, 2022, Odyssey.

Probing Deep Speaker Embeddings for Speaker-related Tasks

Junyi Peng, Rongzhi Gu, Zifeng Zhao, 2022, 2212.07068.

Improving Speaker Verification with Self-Pretrained Transformer Models

Junyi Peng, Themos Stafylakis, Ladislav Movsner, 2023, INTERSPEECH.

Alleviate Cross-chunk Permutation through Chunk-level Speaker Embedding for Blind Speech Separation

Yuexian Zou, Rongzhi Gu, Dong Yu, 2019, 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Discriminative Feature Learning for Speech Emotion Recognition

Yuexian Zou, Yuying Zhang, Dongyan Huang, 2019, ICANN.

An Attention-Based Backend Allowing Efficient Fine-Tuning of Transformer Models for Speaker Verification

L. Burget, Oldrich Plchot, Junyi Peng, 2022, 2022 IEEE Spoken Language Technology Workshop (SLT).

Yuexian Zou, Rongzhi Gu, Junyi Peng, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Functional-structural sub-region graph convolutional network (FSGCN): Application to the prognosis of head and neck cancer with PET/CT imaging

Junyi Peng, Lijun Lu, Wenbing Lv, 2023, Comput. Methods Programs Biomed..