Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.15519 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911464064811008 |
|---|---|
| author | Yang, Yiming Wang, Guangyong Guan, Haixin Long, Yanhua |
| author_facet | Yang, Yiming Wang, Guangyong Guan, Haixin Long, Yanhua |
| contents | Target speech extraction (TSE) typically relies on pre-recorded high-quality enrollment speech, which disrupts user experience and limits feasibility in spontaneous interaction. In this paper, we propose Enroll-on-Wakeup (EoW), a novel framework where the wake-word segment, captured naturally during human-machine interaction, is automatically utilized as the enrollment reference. This eliminates the need for pre-collected speech to enable a seamless experience. We perform the first systematic study of EoW-TSE, evaluating advanced discriminative and generative models under real diverse acoustic conditions. Given the short and noisy nature of wake-word segments, we investigate enrollment augmentation using LLM-based TTS. Results show that while current TSE models face performance degradation in EoW-TSE, TTS-based assistance significantly enhances the listening experience, though gaps remain in speech recognition accuracy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15519 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Enroll-on-Wakeup: A First Comparative Study of Target Speech Extraction for Seamless Interaction in Real Noisy Human-Machine Dialogue Scenarios Yang, Yiming Wang, Guangyong Guan, Haixin Long, Yanhua Audio and Speech Processing Sound Target speech extraction (TSE) typically relies on pre-recorded high-quality enrollment speech, which disrupts user experience and limits feasibility in spontaneous interaction. In this paper, we propose Enroll-on-Wakeup (EoW), a novel framework where the wake-word segment, captured naturally during human-machine interaction, is automatically utilized as the enrollment reference. This eliminates the need for pre-collected speech to enable a seamless experience. We perform the first systematic study of EoW-TSE, evaluating advanced discriminative and generative models under real diverse acoustic conditions. Given the short and noisy nature of wake-word segments, we investigate enrollment augmentation using LLM-based TTS. Results show that while current TSE models face performance degradation in EoW-TSE, TTS-based assistance significantly enhances the listening experience, though gaps remain in speech recognition accuracy. |
| title | Enroll-on-Wakeup: A First Comparative Study of Target Speech Extraction for Seamless Interaction in Real Noisy Human-Machine Dialogue Scenarios |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2602.15519 |