An Attention-Based Backend Allowing Efficient Fine-Tuning of Transformer Models for Speaker Verification-Reference-Cited by-同舟云学术

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

Published:2023-01-09 Issue: Volume: Page:
ISSN:
Container-title:2022 IEEE Spoken Language Technology Workshop (SLT)
language:
Short-container-title:

Author:

Peng Junyi¹,Plchot Oldrich¹,Stafylakis Themos²,Mosner Ladislav¹,Burget Lukas¹,Cernocky Jan¹

Affiliation:

1. Brno University of Technology,Faculty of Information Technology, Speech@FIT,Czechia

2. Omilia - Conversational Intelligence,Athens,Greece

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10022052/10022330/10022775.pdf?arnumber=10022775

Reference30 articles.

1. A fine-tuned wav2vec 2.0/hubert benchmark for speech emotion recognition, speaker verification and spoken language understanding;wang;ArXiv Preprint,2021

2. SUPERB: Speech Processing Universal PERformance Benchmark

3. Attention is all you need;vaswani;Advances in neural information processing systems,2017

4. Fine-Tuning Wav2Vec2 for Speaker Recognition

5. Overcoming catastrophic forgetting in neural networks

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Probing Self-Supervised Learning Models With Target Speech Extraction;2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW);2024-04-14

2. Target Speech Extraction with Pre-Trained Self-Supervised Learning Models;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. Dual Parameter-Efficient Fine-Tuning for Speaker Representation Via Speaker Prompt Tuning and Adapters;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

4. Introducing Multilingual Phonetic Information to Speaker Embedding for Speaker Verification;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

5. Leveraging ASR Pretrained Conformers for Speaker Verification Through Transfer Learning and Knowledge Distillation;IEEE/ACM Transactions on Audio, Speech, and Language Processing;2024