1 code implementation • 1 Dec 2020 • Daren Wang, Zifeng Zhao, Yi Yu, Rebecca Willett
We derive finite sample theoretical guarantees and show that the excess prediction risk of our estimator is minimax optimal.
Statistics Theory Methodology Statistics Theory
no code implementations • 4 Apr 2022 • Zifeng Zhao, Dongchao Yang, Rongzhi Gu, Haoran Zhang, Yuexian Zou
However, its performance is often inferior to that of a blind source separation (BSS) counterpart with a similar network architecture, due to the auxiliary speaker encoder may sometimes generate ambiguous speaker embeddings.
no code implementations • 15 Apr 2022 • Zifeng Zhao, Rongzhi Gu, Dongchao Yang, Jinchuan Tian, Yuexian Zou
Dominant researches adopt supervised training for speaker extraction, while the scarcity of ideally clean corpus and channel mismatch problem are rarely considered.
no code implementations • 14 Dec 2022 • Zifeng Zhao, Ding Pan, Junyi Peng, Rongzhi Gu
Results show that all deep embeddings encoded channel and content information in addition to speaker identity, but the extent could vary and their performance on speaker-related tasks can be tremendously different: ECAPA-TDNN is dominant in discriminative tasks, and d-vector leads the guiding tasks, while regulating task is less sensitive to the choice of speaker representations.