Multi-stage Speaker Extraction with Utterance and Frame-Level Reference Signals

Speaker extraction requires a sample speech from the target speaker as the reference. However, enrolling a speaker with a long speech is not practical. We propose a speaker extraction technique, that performs in multiple stages to take full advantage of short reference speech sample. The extracted s...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Ge, Meng, Xu, Chenglin, Wang, Longbiao, Chng, Eng Siong, Dang, Jianwu, Li, Haizhou
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 02.04.2021
Subjects
Balances (scales)
Embedding
Reference signals
Speech
Speech recognition
Online AccessGet full text

Cover

More Information
Summary:Speaker extraction requires a sample speech from the target speaker as the reference. However, enrolling a speaker with a long speech is not practical. We propose a speaker extraction technique, that performs in multiple stages to take full advantage of short reference speech sample. The extracted speech in early stages is used as the reference speech for late stages. For the first time, we use frame-level sequential speech embedding as the reference for target speaker. This is a departure from the traditional utterance-based speaker embedding reference. In addition, a signal fusion scheme is proposed to combine the decoded signals in multiple scales with automatically learned weights. Experiments on WSJ0-2mix and its noisy versions (WHAM! and WHAMR!) show that SpEx++ consistently outperforms other state-of-the-art baselines.
ISSN:2331-8422