# Enroll-on-Wakeup: A First Comparative Study of Target Speech Extraction for Seamless Interaction in Real Noisy Human-Machine Dialogue Scenarios

arXiv: https://arxiv.org/abs/2602.15519 · HTML: https://mlsanity.com/paper/2602.15519/

## Key facts

- No citing papers in the map yet (data through 19 Oct 2026).
- Placed in Audio language models and spoken dialogue, one of 11 directions in Speech and audio language models.
- Builds on 31 of its 36 references that are in the map.
- First posted on arXiv 17 Feb 2026.

## Placed in

- Speech and audio language models / [Audio language models and spoken dialogue](https://mlsanity.com/speech/audio-language-models-and-spoken-dialogue/)

## Builds on (most cited first, 30 of 31)

- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Why gradient clipping accelerates training: A theoretical justification for adaptivity](https://mlsanity.com/paper/1905.11881/) (2019)
- [DNSMOS P.835: A Non-Intrusive Perceptual Objective Speech Quality Metric to Evaluate Noise Suppressors](https://mlsanity.com/paper/2110.01763/) (2021)
- [Deep clustering: Discriminative embeddings for segmentation and separation](https://mlsanity.com/paper/1508.04306/) (2015)
- [WHAM!: Extending Speech Separation to Noisy Environments](https://mlsanity.com/paper/1907.01160/) (2019)
- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [LibriMix: An Open-Source Dataset for Generalizable Speech Separation](https://mlsanity.com/paper/2005.11262/) (2020)
- [CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training](https://mlsanity.com/paper/2505.17589/) (2025)
- [Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit](https://mlsanity.com/paper/2210.17016/) (2022)
- [IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech](https://mlsanity.com/paper/2506.21619/) (2025)
- [VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking](https://mlsanity.com/paper/1810.04826/) (2018)
- [TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation](https://mlsanity.com/paper/2211.12433/) (2022)
- [Dual-Path Transformer Network: Direct Context-Aware Modeling for End-to-End Monaural Speech Separation](https://mlsanity.com/paper/2007.13975/) (2020)
- [WHAMR!: Noisy and Reverberant Single-Channel Speech Separation](https://mlsanity.com/paper/1910.10279/) (2019)
- [SpEx+: A Complete Time Domain Speaker Extraction Network](https://mlsanity.com/paper/2005.04686/) (2020)
- [SpEx: Multi-Scale Time Domain Speaker Extraction Network](https://mlsanity.com/paper/2004.08326/) (2020)
- [MeetEval: A Toolkit for Computation of Word Error Rates for Meeting Transcription Systems](https://mlsanity.com/paper/2307.11394/) (2023)
- [Fun-ASR Technical Report](https://mlsanity.com/paper/2509.12508/) (2025)
- [AV-SepFormer: Cross-Attention SepFormer for Audio-Visual Target Speaker Extraction](https://mlsanity.com/paper/2306.14170/) (2023)
- [TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and Enhancement](https://mlsanity.com/paper/2408.03440/) (2024)
- [L-SpEx: Localized Target Speaker Extraction](https://mlsanity.com/paper/2202.09995/) (2022)
- [SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline](https://mlsanity.com/paper/2505.19314/) (2025)
- [Target Speaker Extraction by Directly Exploiting Contextual Information in the Time-Frequency Domain](https://mlsanity.com/paper/2402.17146/) (2024)
- [USEF-TSE: Universal Speaker Embedding Free Target Speaker Extraction](https://mlsanity.com/paper/2409.02615/) (2024)
- [MC-SpEx: Towards Effective Speaker Extraction with Multi-Scale Interfusion and Conditional Speaker Modulation](https://mlsanity.com/paper/2306.16250/) (2023)
- [Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction](https://mlsanity.com/paper/2310.19644/) (2023)
- [SEF-PNet: Speaker Encoder-Free Personalized Speech Enhancement with Local and Global Contexts Aggregation](https://mlsanity.com/paper/2501.11274/) (2025)
- [MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues](https://mlsanity.com/paper/2412.08247/) (2024)
- [Listen to Extract: Onset-Prompted Target Speaker Extraction](https://mlsanity.com/paper/2505.05114/) (2025)

## Abstract (arXiv)

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.