[go: up one dir, main page]

Follow
Junyi Peng
Junyi Peng
Brno University of Technology
Verified email at fit.vut.cz
Title
Cited by
Cited by
Year
An attention-based backend allowing efficient fine-tuning of transformer models for speaker verification
J Peng, O Plchot, T Stafylakis, L Mošner, L Burget, J Černocký
2022 IEEE Spoken Language Technology Workshop (SLT), 555-562, 2023
65*2023
Parameter-efficient transfer learning of pre-trained transformer models for speaker verification using adapters
J Peng, T Stafylakis, R Gu, O Plchot, L Mošner, L Burget, J Černocký
ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023
382023
Target speech extraction with pre-trained self-supervised learning models
J Peng, M Delcroix, T Ochiai, O Plchot, S Araki, J Černocký
ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024
222024
Improving speaker verification with self-pretrained transformer models
J Peng, O Plchot, T Stafylakis, L Mošner, L Burget, J Černocký
arXiv preprint arXiv:2305.10517, 2023
182023
Progressive contrastive learning for self-supervised text-independent speaker verification
J Peng, C Zhang, J Černocký, D Yu
Proc. Odyssey 2022, 17-24, 2022
142022
BUT systems and analyses for the ASVspoof 5 challenge
J Rohdin, L Zhang, O Plchot, V Staněk, D Mihola, J Peng, T Stafylakis, ...
arXiv preprint arXiv:2408.11152, 2024
102024
ESPnet-SpeechLM: An open speech language model toolkit
J Tian, J Shi, W Chen, S Arora, Y Masuyama, T Maekaku, Y Wu, J Peng, ...
arXiv preprint arXiv:2502.15218, 2025
92025
Probing self-supervised learning models with target speech extraction
J Peng, M Delcroix, T Ochiai, O Plchot, T Ashihara, S Araki, J Černocký
2024 IEEE International Conference on Acoustics, Speech, and Signal …, 2024
82024
ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform
J Peng, X Qu, J Wang, R Gu, J Xiao, L Burget, J Černocký
Proc. Interspeech 2021, 511-515, 2021
82021
Effective Phase Encoding for End-To-End Speaker Verification
J Peng, X Qu, R Gu, J Wang, J Xiao, L Burget, J Černocký
Proc. Interspeech 2021, 2366-2370, 2021
72021
CA-MHFA: A Context-Aware Multi-Head Factorized Attentive Pooling for SSL-Based Speaker Verification
J Peng, L Mošner, L Zhang, O Plchot, T Stafylakis, L Burget, J Černocký
ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and …, 2025
62025
SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
H Wang, J Hai, D Yang, C Chen, K Li, J Peng, T Thebaud, LM Velazquez, ...
arXiv preprint arXiv:2505.19314, 2025
52025
Probing deep speaker embeddings for speaker-related tasks
Z Zhao, D Pan, J Peng, R Gu
arXiv preprint arXiv:2212.07068, 2022
52022
Learnable Sparse Filterbank for Speaker Verification.
J Peng, R Gu, L Mosner, O Plchot, L Burget, J Cernocký
INTERSPEECH, 5110-5114, 2022
52022
Investigation of speaker representation for target-speaker speech processing
T Ashihara, T Moriya, S Horiguchi, J Peng, T Ochiai, M Delcroix, ...
2024 IEEE Spoken Language Technology Workshop (SLT), 423-430, 2024
42024
Multi-channel extension of pre-trained models for speaker verification
L Mošner, R Serizel, L Burget, O Plchot, E Vincent, J Peng, J Černocký
Interspeech, 2024
42024
Deep Speaker Embedding with Long Short Term Centroid Learning for Text-Independent Speaker Verification.
J Peng, R Gu, Y Zou
INTERSPEECH, 3246-3250, 2020
42020
Syllable-dependent discriminative learning for small footprint text-dependent speaker verification
J Peng, Y Zou, N Li, D Tuo, D Su, M Yu, C Zhang, D Yu
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019
42019
Speaker-discriminative embedding learning via affinity matrix for short utterance speaker verification
J Peng, R Gu, Y Zou, W Wang
2019 Asia-Pacific Signal and Information Processing Association Annual …, 2019
42019
Discriminative feature learning for speech emotion recognition
Y Zhang, Y Zou, J Peng, D Luo, D Huang
International Conference on Artificial Neural Networks, 198-210, 2019
32019
The system can't perform the operation now. Try again later.
Articles 1–20