Listen to Extract: Onset-Prompted Target Speaker Extraction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915598071496704 |
|---|---|
| author | Shen, Pengjie Chen, Kangrui He, Shulin Chen, Pengru Yuan, Shuqi Kong, He Zhang, Xueliang Wang, Zhong-Qiu |
| author_facet | Shen, Pengjie Chen, Kangrui He, Shulin Chen, Pengru Yuan, Shuqi Kong, He Zhang, Xueliang Wang, Zhong-Qiu |
| contents | We propose listen to extract (LExt), a highly-effective while extremely-simple algorithm for monaural target speaker extraction (TSE). Given an enrollment utterance of a target speaker, LExt aims at extracting the target speaker from the speaker's mixed speech with other speakers. For each mixture, LExt concatenates an enrollment utterance of the target speaker to the mixture signal at the waveform level, and trains deep neural networks (DNN) to extract the target speech based on the concatenated mixture signal. The rationale is that, this way, an artificial speech onset is created for the target speaker and it could prompt the DNN (a) which speaker is the target to extract; and (b) spectral-temporal patterns of the target speaker that could help extraction. This simple approach produces strong TSE performance on multiple public TSE datasets including WSJ0-2mix, WHAM! and WHAMR!. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_05114 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Listen to Extract: Onset-Prompted Target Speaker Extraction Shen, Pengjie Chen, Kangrui He, Shulin Chen, Pengru Yuan, Shuqi Kong, He Zhang, Xueliang Wang, Zhong-Qiu Audio and Speech Processing Sound We propose listen to extract (LExt), a highly-effective while extremely-simple algorithm for monaural target speaker extraction (TSE). Given an enrollment utterance of a target speaker, LExt aims at extracting the target speaker from the speaker's mixed speech with other speakers. For each mixture, LExt concatenates an enrollment utterance of the target speaker to the mixture signal at the waveform level, and trains deep neural networks (DNN) to extract the target speech based on the concatenated mixture signal. The rationale is that, this way, an artificial speech onset is created for the target speaker and it could prompt the DNN (a) which speaker is the target to extract; and (b) spectral-temporal patterns of the target speaker that could help extraction. This simple approach produces strong TSE performance on multiple public TSE datasets including WSJ0-2mix, WHAM! and WHAMR!. |
| title | Listen to Extract: Onset-Prompted Target Speaker Extraction |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2505.05114 |