# A Hybrid Continuity Loss to Reduce Over-Suppression for Time-domain Target Speaker Extraction

arXiv: https://arxiv.org/abs/2203.16843 · HTML: https://mlsanity.com/paper/2203.16843/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2022.

## Built on by (most cited first, 7 of 7)

- [X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusion](https://mlsanity.com/paper/2303.05023/) (2023)
- [Plug-and-Play Co-Occurring Face Attention for Robust Audio-Visual Speaker Extraction](https://mlsanity.com/paper/2505.20635/) (2025)
- [Late Audio-Visual Fusion for In-The-Wild Speaker Diarization](https://mlsanity.com/paper/2211.01299/) (2022)
- [AV-CrossNet: an Audiovisual Complex Spectral Mapping Network for Speech Separation By Leveraging Narrow- and Cross-Band Modeling](https://mlsanity.com/paper/2406.11619/) (2024)
- [Causal Self-supervised Pretrained Frontend with Predictive Code for Speech Separation](https://mlsanity.com/paper/2504.02302/) (2025)
- [Audio-Visual Speech Enhancement In Complex Scenarios With Separation And Dereverberation Joint Modeling](https://mlsanity.com/paper/2510.26825/) (2025)
- [Adapting Personalized Speech Enhancement for Low-Latency Audio-Visual Target-Speaker Extraction](https://mlsanity.com/paper/2609.30631/) (2026)

## Abstract (arXiv)

The speaker extraction algorithm extracts the target speech from a mixture speech containing interference speech and background noise. The extraction process sometimes over-suppresses the extracted target speech, which not only creates artifacts during listening but also harms the performance of downstream automatic speech recognition algorithms. We propose a hybrid continuity loss function for time-domain speaker extraction algorithms to settle the over-suppression problem. On top of the waveform-level loss used for superior signal quality, i.e., SI-SDR, we introduce a multi-resolution delta spectrum loss in the frequency-domain, to ensure the continuity of an extracted speech signal, thus alleviating the over-suppression. We examine the hybrid continuity loss function using a time-domain audio-visual speaker extraction algorithm on the YouTube LRS2-BBC dataset. Experimental results show that the proposed loss function reduces the over-suppression and improves the word error rate of speech recognition on both clean and noisy two-speakers mixtures, without harming the reconstructed speech quality.