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

arXiv: https://arxiv.org/abs/2011.09624 · HTML: https://mlsanity.com/paper/2011.09624/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2020.

## Built on by (most cited first, 2 of 2)

- [token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and Text](https://mlsanity.com/paper/2210.16755/) (2022)
- [Contrastive Knowledge Distillation for Embedding Refinement in Personalized Speech Enhancement](https://mlsanity.com/paper/2601.16235/) (2026)

## Abstract (arXiv)

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.