# Continuous Speech Separation Using Speaker Inventory for Long Multi-talker Recording

arXiv: https://arxiv.org/abs/2012.09727 · HTML: https://mlsanity.com/paper/2012.09727/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [A Review of Speaker Diarization: Recent Advances with Deep Learning](https://mlsanity.com/paper/2101.09624/) (2021)
- [Directed Speech Separation for Automatic Speech Recognition of Long Form Conversational Speech](https://mlsanity.com/paper/2112.05863/) (2021)
- [Disentangling the Impacts of Language and Channel Variability on Speech Separation Networks](https://mlsanity.com/paper/2203.16040/) (2022)
- [Closing the Gap between Single-User and Multi-User VoiceFilter-Lite](https://mlsanity.com/paper/2202.12169/) (2022)
- [VCSE: Time-Domain Visual-Contextual Speaker Extraction Network](https://mlsanity.com/paper/2210.06177/) (2022)

## Abstract (arXiv)

Leveraging additional speaker information to facilitate speech separation has received increasing attention in recent years. Recent research includes extracting target speech by using the target speaker's voice snippet and jointly separating all participating speakers by using a pool of additional speaker signals, which is known as speech separation using speaker inventory (SSUSI). However, all these systems ideally assume that the pre-enrolled speaker signals are available and are only evaluated on simple data configurations. In realistic multi-talker conversations, the speech signal contains a large proportion of non-overlapped regions, where we can derive robust speaker embedding of individual talkers. In this work, we adopt the SSUSI model in long recordings and propose a self-informed, clustering-based inventory forming scheme for long recording, where the speaker inventory is fully built from the input signal without the need for external speaker signals. Experiment results on simulated noisy reverberant long recording datasets show that the proposed method can significantly improve the separation performance across various conditions.